The Sparse Manifold Transform
|
|
- Todd Jordan
- 5 years ago
- Views:
Transcription
1 The Sparse Manifold Transform Bruno Olshausen Redwood Center for Theoretical Neuroscience, Helen Wills Neuroscience Institute, and School of Optometry UC Berkeley with Yubei Chen (EECS) and Dylan Paiton (Vision Science) NSF RI: Extracting and understanding sparse structure in spatiotemporal data, PI: Sommer
2 Dylan Paiton Yubei Chen Redwood Center for Theoretical Neuroscience - April 2016
3 Are there principles? God is a hacker Francis Crick Individual nerve cells were formerly thought to be unreliable This was quite wrong, and we now realise their apparently erratic behavior was caused by our ignorance, not the neuron s incompetence. H.B. Barlow (1972)
4 Wallisch & Movshon (2008) Gabor filters..?.. objects. faces
5 Three principles of unsupervised learning Sparse coding feature selectivity Manifold flattening equivariance Persistence invariance
6 Sparse coding
7 The Ratio Club (1952) Horace Barlow
8
9 V1 is highly overcomplete LGN afferents IVb layer 4 cortex Barlow (1981) 0 1mm C I b and IV
10 ... Sparse coding External world Internal model image model (Olshausen & Field, 1996; Chen, Donoho & Saunders 1995) I(x,y) φ i (x,y) ai MX I( x) = a i i ( x)+ ( x) i=1 image neural features other activities stuff (sparse)
11 Energy function preserve information be sparse
12 <latexit sha1_base64="4yfjz/utdtr7dp3o4qvddyy2i2i=">aaab6xicbvbns8naej3ur1q/qh69lbbbu0le0gpri8cq9gpaudbbsbt0swm7g6ge/gmvhhtx6j/y5r9x0+agrq8ghu/nmdmvsatxxnw/ndla+sbmvnm7sro7t39qptxq6zhvdfssfrhqblsj4bjbhhub3uqhjqkbnwbym/udj1sax/lrtbp0izqsposmgis9jcqdas2tu3oqveivpayfmopqv38yszrcazigwvc8nzf+rpxhtocs0k81jprn6ah7lkoaofaz+auzcmaviqljzusamld/t2q00noabbyzomasl71c/m/rpsa89jmuk9sgzitfysqiiun+nhlyhcyiqswukw5vjwxmfwxghpoh4c2/veraf3xprxv3l7xgtrfhgu7gfm7bgytowb00oqumqnigv3hzjs6l8+58lfpltjfzdh/gfp4aapem/w==</latexit> Locally Competitive Algorithm (LCA) minimizes the energy function (Rozell, Johnson, Baraniuk & Olshausen, 2008) b i = X x i(x) I(x) G ij = X x i(x) j (x)
13 Learned dictionary { i } spatial frequency (cycles/window) y x Olshausen & Field (1996)
14 Sparse encoding of a time-varying image image sparse encoding reconstruction
15 Sparse coefficient activations form smooth trajectories in particular local subspaces
16 Basis functions tile the manifold of natural images in such a way that data points along the manifold are spanned by a small number of basis vectors.
17 Manifold flattening
18 Science, 22 Dec. 2000
19 Local Linear Embedding (LLE) exactly such transformations. We th expect their characterization of local g try in the original data space to be valid for local patches on the manif particular, the same weights W ij that struct the ith data point in D dime should also reconstruct its embedded fold coordinates in d dimensions. LLE constructs a neighborhood-pre mapping based on the above idea. In th step of the algorithm, each high-dime ε W X i j W ijxj 2 observation X i is mapped to a low-dime vector Yi representing i global internal nates on the manifold. This is done by ch d-dimensional coordinates Y i to minim embedding cost function Y i Y i j W ij Yj 2 This cost function, like the previous based on locally linear reconstruction but here we fix the weights W whil
20 <latexit sha1_base64="nco/reiwdp/2joqbhwmf/bk9w30=">aaab6nicbvbns8naej3ur1q/oh69lbbbu0le0gpri8ek9gpaudbbtbt0swm7e6ge/gqvhhtx6i/y5r9x2+agrq8ghu/nmdmvtkuw6hnftmltfwnzq7xd2dnd2z9wd49ajsk0402wyer3qmq4fio3uadknvrzgoest8px7cxvp3ftrkieczlyikzdjslbkfrpodexfbfq1bw5ycrxc1kfao2++9ubjcyluuimqtfd30sxyklgwssfvnqz4sllyzrkxusvjbkj8vmpu3jmlqgjem1lizmrvydyghsziupbgvmcmwvvjv7ndtomroncqdrdrthiuzrjggmz/u0gqnogcmijzvrywwkbuu0z2nqqngr/+evv0rqo+v7nv7+s1m+kompwaqdwdj5cqr3uoafnydcez3ifn0c6l86787foltnfzdh8gfp5ayogjba=</latexit> Local Linear Landmarks (LLL) (Vladymyrov & Carreira-Perpinán, 2013)
21 From 1-sparse to k-sparse 1-sparse k-sparse Interpolation by KNN data vectors Interpolation by landmarks or dictionary
22 Topographic ICA (Hyvärinen & Hoyer 2001)
23 f filters as a function of time (horizontal axis) a Hyvärinen et al. Vol. 20, No. 7/July 2003/J. Opt. Soc. Am. A Bubbles: a unifying framework for low-level statistical properties of natural image sequences Aapo Hyvärinen, Jarmo Hurri, and Jaakko Väyrynen Neural Networks Research Centre, Helsinki University of Technology, P.O. Box 9800, FIN HUT, Finland
24 Sparse Manifold Transform (Yubei Chen, Ph.D. thesis) The Sparse Manifold Transform x (R2 )... 1 <latexit sha1_base64="5gzcxzr7alhkdfo5i9imea1bwm8=">aaacghicbvdlsgmxfm3uv62vqks3wsiiap0pgoiirtcuk9ghnlxcsdm2njmzkoxy2n6gg3/fjqtf3hbn35g+ftp6ihbyzr03ucepbnfgdb+dxmli0vjkcjw1tr6xuzxe3inpmfaufwkoqlxxqtpbjssabgsrripb4atw9js3i7/8yjtmobw33yjvamhj3uqujjxq6vmcimrdfqhviggxdscxun9/oigfnifh0o8/5i6isambyk+pejrjzt0x8dzxpisdpiju00pscgkcmgmoak2rnhuzwg+u4vswqyremkvao9bivuslbezxeupfbvjakg3cdju90ucx+rujb4hw3cc3lqgytp71ruj/xju2zytaj8sonkzsyupnwgat4lfkumevo0z0lqgqup0rpm1qqi3nchscn7vypcnlsp6b9e7omvnrarxjtif20shy0dnko1tuqeve0tn6re/ow3lx3pxp52tsmncmpbvod5zhdzr/nzm=</latexit> xlocal (R2 ) <latexit sha1_base64="t6pxhkk2gehiw53zqxezgsfoieo=">aaab63icbvbns8naej3ur1q/qh69lbbbu0lu0gpri8ck9gpaudbbtbt0dxn2j0ij/qtepcji1t/kzx9j0uagrq8ghu/nmdmvikww6lrftmltfwnzq7xd2dnd2z+ohh61bzqyxlsskphpbtryktrvoudju7hhvawsd4ljxe53nrixitkpoi25r+hii1awirnuhfxwbtwaw3fnikvek0gncjqh1a/+mgkj4hqzpnb2pddgp6ugbzn8vuknlseuteii9zkqqelwt+e3zshzpgxjgjmsnjk5+nsipcraqqqytkvxbje9xpzp6yuy3vip0hgcxlpfojcrbcosp06gwncgcporyozibivsta1lmmwth+atv7xk2hd1z617d1e1xm0rrxlo4btowynrama9nkefdmbwdk/w5ijnxxl3phatjaeyoyy/cd5/aaa6jy4=</latexit> <latexit sha1_base64="sfmtfy2viq9fo+d+czscmwtazbs=">aaab63icbvbns8naej3ur1q/qh69lbbbu0leqmeif48v7ae0owy2m3bp7ibstoqs+he8efdeq3/im//gpm1bwx8mpn6bywzeeeth0xw/ndlg5tb2tnm3srd/chhupt7p2cgxjldzjcptc6jlumjerogs92ldqqok7wbtu9zvpnfjraqfcrzzx9gxfqfgfhopnfqqw2rnrbslkhxifaqgbvrd6tdgflfecy1mumv7nhujn1kdgkk+rwwsy2pkpntm+xnvvhhrp4tb5+qiu0ykjexwgslc/t2rumxttavzp6i4satelv7n9rmmb/xu6dhbrtlyuzhighhjhycjythdocsizuzktxi2oyyyzoljq/bwx14nnau659a9h+ta87aiowxnca6x4eedmnaplwgdgwk8wyu8ocp5cd6dj2vryslmtuepnm8fa7cnja==</latexit> <latexit sha1_base64="5vl7yz45j79uamdessxsrgtv2zc=">aaab63icbvbns8naej3ur1q/qh69lbbbu0mkomeif48v7ae0owy2m3bp7ibstoqs+he8efdeq3/im//gpm1bwx8mpn6bywzeeeth0xw/ndlg5tb2tnm3srd/chhupt7p2cgxjldzjcptc6jlumjerogs92ldqqok7wbtu9zvpnfjraqfcrzzx9gxfqfgfhopnwxuhtwaw3cxiovek0gncrsg1a/bkgkj4hqzpnb2ptdgp6ugbzn8xhkklseutemy9zoqqelwtxe3zslfpoxigjmsnjkf+nsipcramqqytkvxyle9xpzp6ycy3vip0hgcxlplojcrbcosp05gwncgcpyryozibivsqg1lmmwth+ctvrxooo2659a9h6ta87aiowxnca6x4me1noeewtagbhn4hld4c5tz4rw7h8vwklpmnmifoj8/btwnjq==</latexit> 2 <latexit sha1_base64="m6whpsvc0ahh0zceaoguhblate0=">aaab63icbvbns8naej3ur1q/qh69lbbbu0mkomeif48v7ae0owy2m3bp7ibstoqs+he8efdeq3/im//gpm1bwx8mpn6bywzeeeth0xw/ndlg5tb2tnm3srd/chhupt7p2cgxjldzjcptc6jlumjerogs92ldqqok7wbtu9zvpnfjraqfcrzzx9gxfqfgfhopnwxuhtwaw3cxiovek0gncrsg1a/bkgkj4hqzpnb2ptdgp6ugbzn8xhkklseutemy9zoqqelwtxe3zslfpoxigjmsnjkf+nsipcramqqytkvxyle9xpzp6ycy3vip0hgcxlplojcrbcosp05gwncgcpyryozibivsqg1lmmwth+ctvrxoold1z617d41a87aiowxnca6x4me1noeewtagbhn4hld4c5tz4rw7h8vwklpmnmifoj8/cd+njw==</latexit> 4 Dictionary elements learned from natural signals with sparse coding may be conceptualized as landmarks on a smooth m nction defined on R2 (e.g. a gray-scale natural image) and one element from its reconstruction are represented by the b
25 Persistence
26 <latexit sha1_base64="s8btnv4fqa19yel5zrbiyd8tbti=">aaab9hicbvbns8naej3ur1q/qh69lbbbqymjcopbkhrrw4smltrp2wy37dlnb7sbpyt+dy8evlz6y7z5b9y0owjrg4hhezpmzpnjzqqyzw+jslk6tr5r3cxtbe/s7px3d5oysgshdol4jno+lpszkdqkku7bsaa48dlt+epbzg89uifzfdbujkzegichgzcclza6tlttulw720dx6l7uk1fmmjkdwizwtiqqw+6vv9x+rjkahopwlgxhmmplpvgorjidltxe0hitmr7sjqyhdqj00tnvu3silt4arejxqnbm/t2r4kdksedrzgcrkvz0mve/r5oowawxsjbofa3jfneg4uhfkisa9zmgrpgjjpgipm9fziqfjkohlyvglb68tjyz2lxnejiv1g/ynipwbmdwchzcqb3uwayhcah4hld4m56mf+pd+ji3fox85hd+wpj8afbqkgi=</latexit> <latexit sha1_base64="6o+ggnzwibydht7xsxvuuj+gogk=">aaab/hicbvdlssnafj34rpuvhzs3g0wom5kioc6eyjcuk5i20iqymu7aofmim5nidcvfcencxa0f4s6/mwm70nydfw7n3mu994qxo9o4zre1tlyyurze2chubm3v7np7+w0te4wjhywtqhuitrgvxdpumnkkfue8zkqzdmq53xwspaku92yuk4cjnqarxchkusc+bfz7pjqpqa84rmnhuixoix275fscceaicwekbgaod+wvvytxwokwmcgt264tmybfyldmyljoj5reca9qj7qzkhanokgn14/hsaz0ysrvvslaifp7ikvc6xeps06otf/pe7n4n9dothqzpfteisectxdfcyngwjwk2kwkymnggufy0exwiptiiwyywpiq3pmxf4l3vrmquhfnpernli0coalhoaxccagq4bbugqcweatp4bw8wu/wi/vufuxbl6zzzah4a+vzb3udlcm=</latexit> <latexit sha1_base64="6o+ggnzwibydht7xsxvuuj+gogk=">aaab/hicbvdlssnafj34rpuvhzs3g0wom5kioc6eyjcuk5i20iqymu7aofmim5nidcvfcencxa0f4s6/mwm70nydfw7n3mu994qxo9o4zre1tlyyurze2chubm3v7np7+w0te4wjhywtqhuitrgvxdpumnkkfue8zkqzdmq53xwspaku92yuk4cjnqarxchkusc+bfz7pjqpqa84rmnhuixoix275fscceaicwekbgaod+wvvytxwokwmcgt264tmybfyldmyljoj5reca9qj7qzkhanokgn14/hsaz0ysrvvslaifp7ikvc6xeps06otf/pe7n4n9dothqzpfteisectxdfcyngwjwk2kwkymnggufy0exwiptiiwyywpiq3pmxf4l3vrmquhfnpernli0coalhoaxccagq4bbugqcweatp4bw8wu/wi/vufuxbl6zzzah4a+vzb3udlcm=</latexit> <latexit sha1_base64="6o+ggnzwibydht7xsxvuuj+gogk=">aaab/hicbvdlssnafj34rpuvhzs3g0wom5kioc6eyjcuk5i20iqymu7aofmim5nidcvfcencxa0f4s6/mwm70nydfw7n3mu994qxo9o4zre1tlyyurze2chubm3v7np7+w0te4wjhywtqhuitrgvxdpumnkkfue8zkqzdmq53xwspaku92yuk4cjnqarxchkusc+bfz7pjqpqa84rmnhuixoix275fscceaicwekbgaod+wvvytxwokwmcgt264tmybfyldmyljoj5reca9qj7qzkhanokgn14/hsaz0ysrvvslaifp7ikvc6xeps06otf/pe7n4n9dothqzpfteisectxdfcyngwjwk2kwkymnggufy0exwiptiiwyywpiq3pmxf4l3vrmquhfnpernli0coalhoaxccagq4bbugqcweatp4bw8wu/wi/vufuxbl6zzzah4a+vzb3udlcm=</latexit> <latexit sha1_base64="6o+ggnzwibydht7xsxvuuj+gogk=">aaab/hicbvdlssnafj34rpuvhzs3g0wom5kioc6eyjcuk5i20iqymu7aofmim5nidcvfcencxa0f4s6/mwm70nydfw7n3mu994qxo9o4zre1tlyyurze2chubm3v7np7+w0te4wjhywtqhuitrgvxdpumnkkfue8zkqzdmq53xwspaku92yuk4cjnqarxchkusc+bfz7pjqpqa84rmnhuixoix275fscceaicwekbgaod+wvvytxwokwmcgt264tmybfyldmyljoj5reca9qj7qzkhanokgn14/hsaz0ysrvvslaifp7ikvc6xeps06otf/pe7n4n9dothqzpfteisectxdfcyngwjwk2kwkymnggufy0exwiptiiwyywpiq3pmxf4l3vrmquhfnpernli0coalhoaxccagq4bbugqcweatp4bw8wu/wi/vufuxbl6zzzah4a+vzb3udlcm=</latexit> <latexit sha1_base64="mn/vnrfrtbcslw3fcifcphm2ave=">aaab7nicbvbns8naej3ur1q/qh69lbbbg5rebd0wvxisyd+gcwwy3brln5uwuxfk6i/w4kerr/4eb/4bt20o2vpg4pheddpzwlrwbvz32ymtrw9sbpw3kzu7e/sh1cojtk4yrvmljijr3ra1e1yylufgsg6qgmahyj1wfdfzo09maz7irznjwrdjupkiuzrw6vjnefcvsf+tuxv3drjkviluoeczx/3ybwnnyiynfah1z3nte+sodkectst+plmkdixd1rnuysx0km/pnzizqwxilchb0pc5+nsix1jrsrzazhjnsc97m/e/r5ez6cbiuuwzwyrdlioyquxczr+tavemgjgxbkni9lzcr6iqgptqxybglb+8stqxdc+tew9xtczteucztuauzsgda2japtshbrtg8ayv8oakzovz7nwswktomxmmf+b8/gc4go8m</latexit> <latexit sha1_base64="zyzbka08naujytw8pm8jf/uv8du=">aaacfnicbvdlssnafj3uv62vqes3g0uqlcupgrqrd8rlbdmwmhgm02k7dgyszizcsfoxbvwvny5u3io7/8b0sddwaxco59zlvfceeankw9a3kvtyxfpeya8w1ty3nrfm7z26cmojiyndfspmgbrhvbbhu81im5ie8ycrrtc/hpmnbyivdcwdhkte46graidipdpjn8sup8jpakoypjw3do6wrtl0vujfwypodhhnyc2nnxqa+nbbn4tw2rodzhn7sopgippvfrntemecci0zuqplw5h2eiq1xywmc26ssirwh3vjk6mccak8zpzxeb5ksht2qpmv0hcs/p5iefdqwioskypdu7pespzpa8w6c+olvesxjgjpfnvibnuiryhbnpueazbicmkszrdc3emsyz1foqrbnn15njiv8lnzvj0uvi+maetbhtghh8agj6akbkanoacdr/amxsgb8ws8go/gx6q1z0xndsefgj8/b1edxg==</latexit> <latexit sha1_base64="hbiqpjxjpmreebr/fuvewpzyvck=">aaab63icbvbnswmxej3ur1q/qh69bivgqcquchosevfywx5au5rsmm1dk+ysziwy9c948aciv/+qn/+n2xyp2vpg4pheddpzwkrwyz3vg5xw1jc2t8rblz3dvf2d6ufr28sppqxfyxhrbkgme1yxluvwsg6igzghyj1wcpf7nsemdy/vo50mljbkphjekbg51oxfkeg15tw9ofaq8qtsgwlnqfwrp4xpkpmyvbbjer6x2caj2niq2kzstw1lcj2qees5qohkjsjmt87wmvogoiq1k2xxxp09krfpzfsgrlmsozblxi7+5/vsg90egvdjapmii0vrkrcncf44hnlnqbvtrwjv3n2k6zhoqq2lp+jc8jdfxixty7rv1f2hq1rjtoijdcdwcufgwzu04b6a0aiky3igv3hder2gd/sxac2hyuyy/gb9/gb7yy3b</latexit> We seek a geometric mapping f : Φ P, s.t. each of the dictionary elements is mapped to a new vector, Pj = f(φj), where Pj is the j th column of P. Continuous temporal transformations in the input should have a linear flow on M and also in the geometrical embedding space. We desire: Pa t 1 2 Pa t Pa t+1 Objective function: s.t. V =Cov(a) D =
27 <latexit sha1_base64="jtdqacsyhdusarjlvigzoythm8o=">aaab7xicbvdlsgnbeoynrxhfuy9ebopgkeykomegf48rzaosjfrojsmy2zllzlyis/7biwdfvpo/3vwbj8kenlggoajqprsrsgq31ve/vcla+sbmvng7tlo7t39qpjxqgpvqyhpucaxberomugqny61g7uqzjcpbwth4dua3npg2xmkho0lygonq8ggnaj3u7kjirtgrv/yqpwdzjufokpcj3it/dfukpjgtlgo0php4iq0z1jztwaalbmpygnsmq9zxvglmtjjnr52sm6f0yubpv9ksufp7ispymekcuc4y7cgsezpxp6+t2sf1mhgzpjzjulg0sawxisxej32ugbvi4ghszd2thi5qi7uuojilivh+ezu0l6qbxw3ulyu1mzyoipzakzxdafdqgzuoqwmopmizvmkbp7wx7937wlqwvhzmgp7a+/wbi4gpga==</latexit> <latexit sha1_base64="f2yzimwbr/dgjzp6tz360fhrqni=">aaab6hicbvbns8naej3ur1q/qh69lbbbu0le0gpri8cw7ae0owy2k3btzhn2n2ij/qvepcji1z/kzx/jts1bwx8mpn6bywzekaiujet+o4w19y3nrej2awd3b/+gfhju0ngqgdzzlglvcahgwsu2dtcco4lcgguc28h4dua3h1fphst7m0nqj+hq8pazaqzueoqxk27vnyosei8nfchr75e/eooyprfkwwtvuuu5ifezqgxnaqelxqoxowxmh9i1vniitz/nd52sm6smsbgrw9kqufp7iqor1pmosj0rnso97m3e/7xuasjrp+mysq1ktlgupokymmy+jgoukbkxsyqyxe2thi2ooszybeo2bg/55vxsuqh6btvrxfzqn3kcrtibuzghd66gbndqhyywqhigv3hzhpwx5935wlqwnhzmgp7a+fwb5jmm/a==</latexit> <latexit sha1_base64="8mzdy9xwepsvigumrvrx3ipm9ue=">aaab7hicbvbns8naej3ur1q/qh69bivgqsqi6lhoxwmfwwttkjvtpf262ytdivbcf4mxd4p49qd589+4bxpq1gcdj/dmmjkxpliy8rxvp7s2vrg5vd6u7ozu7r9ud4/ajsk0xxzpzki7itmohciwczlystwyojt4gi5vz/7je2ojevvakxsdma2viarnzkvwl0ri/wrnq3tzukvel0gncjt71a/eiofzjiq4zmz0fs+ligeabjc4rfqygynjyzberqwkxwicfh7s1d2zyscnem1lkttxf0/kldzmeoe2m2y0msvetpzp62yuxqe5uglgqphiuzrjlxj39rk7ebo5yykljgthb3x5igngyeztssh4yy+vkvzf3ffq/v1lrxftxfggezifc/dhchpwb01oaqcbz/akb45yxpx352prwnkkmwp4a+fzb8pwjqq=</latexit> <latexit sha1_base64="amrqspawr7hi/mdgqkeukpymg8y=">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</latexit> The sparse manifold transform
28 Simple example
29 rows that were used in the classical embedding are linear Simple ramp functions and the later example rows have higher frequencies. learned embedding rows of P Figure 3. A functional interpretation of manifold embedding. A)
30 Simple example k-sparse function embedding and recovery 4-sparse function <latexit sha1_base64="midukevp9enlmuwsxqos5lab9xm=">aaab7xicbvbns8naej3ur1q/qh69lbbbu0le0gpri8ck9gpaudbbtbt2kw27e6ge/gcvhhtx6v/x5r9x0+agrq8ghu/nmdmvskqw6lrftmltfwnzq7xd2dnd2z+ohh61juo14y2mpnldgbourcxbkfdybqi5jqljo8hknvc7t1wboeihncbcj+gofqfgfk3u7gccawvqrbl1dw6ysryc1kbac1d96g8vsymei5pumj7njuhnvkngks8q/dtwhlijhfgeptgnupgz+buzcmaviqmvthujmau/jziagtonatszurybzs8x//n6kybxfibijeues8wimjuefclfj0ohoum5tyqyleythi2ppgxtqhki3vllq6r9uffcund/wwvcfhgu4qro4rw8uiig3eetwsdgez7hfd4c5bw4787horxkfdph8afo5w/54o64</latexit> recovery
31 <latexit sha1_base64="olishiyhg4ag1upjk4yi4gtsjye=">aaab7nicbvdlsgnbeoz1gemr6thlyba8hv0r9bj04jgceucyhn7jjbkyozvmzaphyud48aciv7/hm3/jblihtsxokkq66e6klodg+v63t7a+sbm1xdop7+7thxxwjo5bjkk1zu2aier3ijrmcmmallvbokozjcpb2thklvfbt0wbnshho1usjhek+zbtte5q91comzb7lapf8+cgqyqosbuknpqvr94gownmpkucjekgvrjhhtpyktis3esnu0gnogjdryxgzitz/nwzoxfkgawt7upamld/t2qygzoni9czox2bzs8x//o6qr3ehbmxkrvm0swiysqituj+oxlwzagvu0eqau5ujxsmgql1ceuhbmsvr5lwzs3wa8hdvbv+w8rrglm4gwsi4brqca8naakfctzdk7x5ynvx3r2preuav8ycwb94nz/b+y8s</latexit> <latexit sha1_base64="au2pysm3bhfn5ul25fiumeti3uw=">aaab6xicbvbns8naej3ur1q/qh69lbbbu0le0gpri8cqthbaudbbtbt0swm7e7ge/gmvhhtx6j/y5r9x0+agrq8ghu/nmdmvskqw6lrftmlldw19o7xz2dre2d2r7h+0tzxqxlsslrhubnrwkrrvoudjo4nmnaokfwjg17n/8mi1ebg6x0nc/ygolqgfo2ilu6dkv1pz6+4mzjl4balbgwa/+tubxcynueimqtfdz03qz6hgwssfvnqp4qllyzrkxusvjbjxs9mlu3jilqejy21lizmpvycyghkziqlbgvecmuuvf//zuimgl34mvjiiv2y+kewlwzjkb5ob0jyhnfhcmrb2vsjgvfognpw8bg/x5wxspqt7bt27pa81roo4ynaex3akhlxaa26gcs1gemizvmkbm3zenhfny95acoqzq/gd5/mhgsynea==</latexit> <latexit sha1_base64="uupgqesxuoeaqokskj/yzfwqzk8=">aaab73icbvbns8naej34wetx1aoxxsj4kokieix68vjbfkabyma7azdunnf3ipbqp+hfgyje/tve/ddu2hy09cha470zzuyfirqgxffbwvldw9/ylg2vt3d29/yrb4cte6ea8salzaw7atvccswbkfdytqi5jqlj28h4jvfbj1wbeat7nctcj+hqivawilbq9eyus6dpuv+pujv3brjmvijuoucjx/nqdwkwrlwhk9syrucm6gduo2cst8u91pcesjed8q6likbc+nns3ik5tcqahlg2pzdm1n8tgy2mmusb7ywojsyil4v/ed0uwys/eypjkss2xxsmkmbm8ufjqgjoue4souwleythi6opqxtrhok3+piyaz3xplfm3v1u69dfhcu4hhm4aw8uoq630iammjdwdk/w5jw4l8678zfvxxgkmsp4a+fzb+ddj90=</latexit> <latexit sha1_base64="midukevp9enlmuwsxqos5lab9xm=">aaab7xicbvbns8naej3ur1q/qh69lbbbu0le0gpri8ck9gpaudbbtbt2kw27e6ge/gcvhhtx6v/x5r9x0+agrq8ghu/nmdmvskqw6lrftmltfwnzq7xd2dnd2z+ohh61juo14y2mpnldgbourcxbkfdybqi5jqljo8hknvc7t1wboeihncbcj+gofqfgfk3u7gccawvqrbl1dw6ysryc1kbac1d96g8vsymei5pumj7njuhnvkngks8q/dtwhlijhfgeptgnupgz+buzcmaviqmvthujmau/jziagtonatszurybzs8x//n6kybxfibijeues8wimjuefclfj0ohoum5tyqyleythi2ppgxtqhki3vllq6r9uffcund/wwvcfhgu4qro4rw8uiig3eetwsdgez7hfd4c5bw4787horxkfdph8afo5w/54o64</latexit> Encoding of a natural video sequence
32 Stacked Sparse Manifold Transform layer 3 layer 2 layer 1
33 <latexit sha1_base64="sld2tr8g7jc72ycmid61qq6ybwm=">aaab83icbvbns8naej34wetx1aoxxslus0lu0gpri8ck9goawdbbabt0swm7g6ge/g0vhhtx6p/x5r9x2+agrq8ghu/nmdmvtatxxnw/nzxvtfwnzcjwcxtnd2+/dhdy1hgqgdzylglvdqlgwsu2ddcc24lcgoucw+hoduq3nlbphsshm04wioha8j5n1fjj9+td/phvls4m3vg3vhar7gxkmxg5kuooerf05fdilkyodrnu647njibiqdkcczwu/vrjqtmidrbjqaqr6icb3twhp1bpkx6sbeldzurviyxgwo+j0hzg1az1ojcv//m6qelfbxmxswpqsvmifiqiick0anljcpkry0sou9zestiqksqmjaloq/awx14mzfoq51a9+8ty7sapowdhcaiv8oakanahdwgagwse4rxennr5cd6dj3nrippphmefoj8/h++rew==</latexit> <latexit sha1_base64="f2yzimwbr/dgjzp6tz360fhrqni=">aaab6hicbvbns8naej3ur1q/qh69lbbbu0le0gpri8cw7ae0owy2k3btzhn2n2ij/qvepcji1z/kzx/jts1bwx8mpn6bywzekaiujet+o4w19y3nrej2awd3b/+gfhju0ngqgdzzlglvcahgwsu2dtcco4lcgguc28h4dua3h1fphst7m0nqj+hq8pazaqzueoqxk27vnyosei8nfchr75e/eooyprfkwwtvuuu5ifezqgxnaqelxqoxowxmh9i1vniitz/nd52sm6smsbgrw9kqufp7iqor1pmosj0rnso97m3e/7xuasjrp+mysq1ktlgupokymmy+jgoukbkxsyqyxe2thi2ooszybeo2bg/55vxsuqh6btvrxfzqn3kcrtibuzghd66gbndqhyywqhigv3hzhpwx5935wlqwnhzmgp7a+fwb5jmm/a==</latexit> <latexit sha1_base64="zinnqoh2wynwzsx2+1u95+kfqfc=">aaab9hicbvdlsgnbeoz1gemr6thlybdijeykomegf48rzaosncxozpmhsw9neonh2e/w4kerr36mn//gsbihtsxokkq66e7yyik02va3tbk6tr6xwdgqbu/s7u2xdg6bokou4w0wyui1paq5fcfvoedj27hinpakb3mjm6nfgnolrrte4ytmbkahofafo2gktzukmd5ld2nfoct6pbjdtwcgy8tjsrly1hulr24/yknaq2ssat1x7bjdlcoutpks2e00jykb0qhvgbrsggs3nr2dkvoj9ikfkvmhkpn6eyklgdatwdodacwhxvsm4n9ej0h/yk1fgcfiqzzf5cesyesmczc+ujyhnbhcmrlmvskgvfggjqeiccfzfhmznm+rjl117i7ktes8jgicwwluwiflqmet1kebdb7hgv7hzrpbl9a79tfvxbhymsp4a+vzb3crkd0=</latexit> <latexit sha1_base64="ifgdmsi+ykpoysbhtqdrbgv1tfi=">aaab83icbvbns8naej34wetx1aoxxslus0lu0gpri8ck9goawdbbabt0swm7g6ge/g0vhhtx6p/x5r9x2+agrq8ghu/nmdmvtatxxnw/nzxvtfwnzcjwcxtnd2+/dhdy1hgqgdzylglvdqlgwsu2ddcc24lcgoucw+hoduq3nlbphsshm04wioha8j5n1fjj9+td/phvls4mxdetld2qownzjl5oypcj3i19+b2yprfkwwtvuuo5iqkyqgxnaidfp9wyudaia+xykmmeoshmn0/iqvv6pb8rw9kqmfp7iqor1umotj0rnuo96e3f/7xoavrxqczlkhqubl6onwpiyjingps4qmbe2blkfle3ejakijjjyyraelzfl5dj87zquvxv/rjcu8njkmaxneafplicgtxbhrraiifneiu3j3venhfny9664uqzr/ahzucpixorfa==</latexit> <latexit sha1_base64="1k82nwtdeqjr9lega9ybtbijwzu=">aaacghicbvbns8naej3ur1q/oh69bitqewpsbt0wvxisyd+giwwz3brln5uwuxfkym/w4l/x4kerr735b9y2owjtg4hhezpmzpnjrqwy7w+jslk6tr5r3cxtbe/s7pn7by0zjqktjo5yjdo+korrtpqkkky6ssao9blp+6pbqd9+iklsid+ocuy8ea04dshgsks989wnbmkpk6w1zg0m6wnautjneqoz5trrmww7as9g/sdotsqqo9ezj24/wkliumimsdl17fh5krkkykaykptieim8qgps1zsjkegvnt2wwsda6vtbjhrxzc3u3xmpcquch77udjeaykvvki7zuokkrr2u8jhrhop5oibhloqsaupwnwqcfrtrgrcg+lyld5foroksszoez/hl/6rvqzp21bm/lndv8jikcathuaehrqaod9cajmb4hld4hw/jxxgzpo2vewvbygco4q+myq+u0z+f</latexit> <latexit sha1_base64="xdqxkquukpbdd2c/afadhdhvwhg=">aaab9hicbvbns8naej3ur1q/qh69bitqlyupgh6lxjxwsb/qxrlzbtulm03cnrrlyo/w4kerr/4yb/4bt20o2vpg4pheddpz/ehwjy7zbexw1jc2t/lbhz3dvf2d4ufru4exoqxbqxgqtk80e1yybniurb0prgjfsjy/vpn5rqltmofyhqcr8wiylhzakuejed0rweqpfujk1fo0vyw5fwcoe5w4gslbhnqv+nxthzqomeqqinyd14nqs4hctgvlc91ys4jqmrmyjqgsbex7yfzo1d4zst8ehmqurhuu/p5iskd1npbnz0bwpje9mfif14lxcoulxeyxmkkxiwaxsdg0zwnyfa4yrte1hfdfza02hrffkjqcciyed/nlvdksvlyn4t5dlgrxwrx5oiftkimll1cdw6hdayg8wjo8wps1sv6sd+tj0zqzsplj+apr8wdyf5he</latexit> <latexit sha1_base64="th+grho07f4emvazxgdptjkv3uc=">aaab9hicbvdjsgnbek2jw4xb1koxxides5hrqy9blx4jmawsmfr0epimpyvdncewzhd48acivz/gm39jzzlo4oocx3tvvnxzyik02va3lvtzxvvfyg8wtrz3dvek+wcnhswk8tqlzkrahtvcipdxuadkrvhxgnisn73hzcrvjrjsigrvcrxzn6d9upicutss2xlqtj+yh7r8fpp1iyw7yk9blokzjywyo9ytfnv6euschiktvou2y8foplshyjjnhu6ieuzzkpz529cqbly76ftojjwypuf8sjkkkuzv3xmpdbqeb57pdcgo9ki3ef/z2gn6v24qwjhbhrlzij+rbcmysyd0hoim5dgqypqwtxi2oioyndkvtajo4svlphfwceykc3drql7p48jderxdgry4hcrcqg3qwoarnuev3qyr9wk9wx+z1pw1nzmep7a+fwbznzhf</latexit> Stacked Sparse Manifold Transform reconstruction from layers 1,2,3 flattening at layer 3
34 ... DiCarlo & Cox (2007)
35 Main points Sparse coding provides a foundation for manifold learning. A geometrical embedding of the dictionary may be learned by exploiting temporal persistence of structure in the visual world. Manifold flattening may be accomplished in a progressive manner by successive stages of sparse coding (dimensionality expansion) and linear projection (dimensionality collapse) in the ventral stream of visual cortex.
Perception as an Inference Problem
Perception as an Inference Problem Bruno A. Olshausen Helen Wills Neuroscience Institute, School of Optometry and Redwood Center for Theoretical Neuroscience UC Berkeley What are the principles governing
More informationFrom natural scene statistics to models of neural coding and representation (part 1)
From natural scene statistics to models of neural coding and representation (part 1) Bruno A. Olshausen Helen Wills Neuroscience Institute, School of Optometry and Redwood Center for Theoretical Neuroscience
More informationThe Sparse Manifold Transform
The Sparse Manifold Transform Yubei Chen 1,2 Dylan M Paiton 1,3 Bruno A Olshausen 1,3,4 1 Redwood Center for Theoretical Neuroscience 2 Department of Electrical Engineering and Computer Science 3 Vision
More informationEmergence of Topography and Complex Cell Properties from Natural Images using Extensions of ICA
Emergence of Topography and Complex Cell Properties from Natural Images using Extensions of ICA Aapo Hyviirinen and Patrik Hoyer Neural Networks Research Center Helsinki University of Technology P.O. Box
More informationLearning Transformational Invariants from Natural Movies
Learning Transformational Invariants from Natural Movies Charles F. Cadieu & Bruno A. Olshausen Helen Wills Neuroscience Institute University of California, Berkeley Berkeley, CA 94720 {cadieu, baolshausen}@berkeley.edu
More informationModeling Visual Cortex V4 in Naturalistic Conditions with Invari. Representations
Modeling Visual Cortex V4 in Naturalistic Conditions with Invariant and Sparse Image Representations Bin Yu Departments of Statistics and EECS University of California at Berkeley Rutgers University, May
More informationSelf-Organizing Sparse Codes
Self-Organizing Sparse Codes Yangqing Jia Sergey Karayev 2010-12-16 Abstract Sparse coding as applied to natural image patches learns Gabor-like components that resemble those found in the lower areas
More informationC. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun
Efficient Learning of Sparse Overcomplete Representations with an Energy-Based Model Marc'Aurelio Ranzato C. Poultney S. Cho pra (NYU Courant Institute) Y. LeCun CIAR Summer School Toronto 2006 Why Extracting
More informationA Hierarchial Model for Visual Perception
A Hierarchial Model for Visual Perception Bolei Zhou 1 and Liqing Zhang 2 1 MOE-Microsoft Laboratory for Intelligent Computing and Intelligent Systems, and Department of Biomedical Engineering, Shanghai
More informationModern Signal Processing and Sparse Coding
Modern Signal Processing and Sparse Coding School of Electrical and Computer Engineering Georgia Institute of Technology March 22 2011 Reason D etre Modern signal processing Signals without cosines? Sparse
More informationCSC 411 Lecture 18: Matrix Factorizations
CSC 411 Lecture 18: Matrix Factorizations Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 18-Matrix Factorizations 1 / 27 Overview Recall PCA: project data
More informationBilinear Models of Natural Images
In: SPIE Proceedings vol. 6492: Human Vision and Electronic Imaging XII, (B.E. Rogowitz, T.N. Pappas, S.J. Daly, Eds.), Jan 28-Feb 1, 2007, San Jose, California Bilinear Models of Natural Images Bruno
More informationNatural image statistics and efficient coding
Network: Computation in Neural Systems 7 (1996) 333 339. Printed in the UK WORKSHOP PAPER Natural image statistics and efficient coding B A Olshausen and D J Field Department of Psychology, Uris Hall,
More informationSelecting Models from Videos for Appearance-Based Face Recognition
Selecting Models from Videos for Appearance-Based Face Recognition Abdenour Hadid and Matti Pietikäinen Machine Vision Group Infotech Oulu and Department of Electrical and Information Engineering P.O.
More informationICA mixture models for image processing
I999 6th Joint Sy~nposiurn orz Neural Computation Proceedings ICA mixture models for image processing Te-Won Lee Michael S. Lewicki The Salk Institute, CNL Carnegie Mellon University, CS & CNBC 10010 N.
More informationHuman Vision Based Object Recognition Sye-Min Christina Chan
Human Vision Based Object Recognition Sye-Min Christina Chan Abstract Serre, Wolf, and Poggio introduced an object recognition algorithm that simulates image processing in visual cortex and claimed to
More informationFast, Accurate Spectral Clustering Using Locally Linear Landmarks
Fast, Accurate Spectral Clustering Using Locally Linear Landmarks Max Vladymyrov Google Inc. Miguel Á. Carreira-Perpiñán EECS, UC Merced May 17, 2017 Spectral clustering Focus on the problem of Spectral
More informationDimension Reduction of Image Manifolds
Dimension Reduction of Image Manifolds Arian Maleki Department of Electrical Engineering Stanford University Stanford, CA, 9435, USA E-mail: arianm@stanford.edu I. INTRODUCTION Dimension reduction of datasets
More informationSPARSE CODES FOR NATURAL IMAGES. Davide Scaramuzza Autonomous Systems Lab (EPFL)
SPARSE CODES FOR NATURAL IMAGES Davide Scaramuzza (davide.scaramuzza@epfl.ch) Autonomous Systems Lab (EPFL) Final rapport of Wavelet Course MINI-PROJECT (Prof. Martin Vetterli) ABSTRACT The human visual
More informationSELECTION OF THE OPTIMAL PARAMETER VALUE FOR THE LOCALLY LINEAR EMBEDDING ALGORITHM. Olga Kouropteva, Oleg Okun and Matti Pietikäinen
SELECTION OF THE OPTIMAL PARAMETER VALUE FOR THE LOCALLY LINEAR EMBEDDING ALGORITHM Olga Kouropteva, Oleg Okun and Matti Pietikäinen Machine Vision Group, Infotech Oulu and Department of Electrical and
More informationLocally Linear Landmarks for large-scale manifold learning
Locally Linear Landmarks for large-scale manifold learning Max Vladymyrov and Miguel Á. Carreira-Perpiñán Electrical Engineering and Computer Science University of California, Merced http://eecs.ucmerced.edu
More informationNon-Differentiable Image Manifolds
The Multiscale Structure of Non-Differentiable Image Manifolds Michael Wakin Electrical l Engineering i Colorado School of Mines Joint work with Richard Baraniuk, Hyeokho Choi, David Donoho Models for
More informationSparse Models in Image Understanding And Computer Vision
Sparse Models in Image Understanding And Computer Vision Jayaraman J. Thiagarajan Arizona State University Collaborators Prof. Andreas Spanias Karthikeyan Natesan Ramamurthy Sparsity Sparsity of a vector
More informationMultiview Feature Learning
Multiview Feature Learning Roland Memisevic Frankfurt, Montreal Tutorial at IPAM 2012 Roland Memisevic (Frankfurt, Montreal) Multiview Feature Learning Tutorial at IPAM 2012 1 / 163 Outline 1 Introduction
More informationSPARSE COMPONENT ANALYSIS FOR BLIND SOURCE SEPARATION WITH LESS SENSORS THAN SOURCES. Yuanqing Li, Andrzej Cichocki and Shun-ichi Amari
SPARSE COMPONENT ANALYSIS FOR BLIND SOURCE SEPARATION WITH LESS SENSORS THAN SOURCES Yuanqing Li, Andrzej Cichocki and Shun-ichi Amari Laboratory for Advanced Brain Signal Processing Laboratory for Mathematical
More informationDetecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference
Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference Minh Dao 1, Xiang Xiang 1, Bulent Ayhan 2, Chiman Kwan 2, Trac D. Tran 1 Johns Hopkins Univeristy, 3400
More informationDetecting Salient Contours Using Orientation Energy Distribution. Part I: Thresholding Based on. Response Distribution
Detecting Salient Contours Using Orientation Energy Distribution The Problem: How Does the Visual System Detect Salient Contours? CPSC 636 Slide12, Spring 212 Yoonsuck Choe Co-work with S. Sarma and H.-C.
More informationEfficient Visual Coding: From Retina To V2
Efficient Visual Coding: From Retina To V Honghao Shan Garrison Cottrell Computer Science and Engineering UCSD La Jolla, CA 9093-0404 shanhonghao@gmail.com, gary@ucsd.edu Abstract The human visual system
More informationNonparametric sparse hierarchical models describe V1 fmri responses to natural images
Nonparametric sparse hierarchical models describe V1 fmri responses to natural images Pradeep Ravikumar, Vincent Q. Vu and Bin Yu Department of Statistics University of California, Berkeley Berkeley, CA
More informationData analysis and inference for an industrial deethanizer
Data analysis and inference for an industrial deethanizer Francesco Corona a, Michela Mulas b, Roberto Baratti c and Jose Romagnoli d a Dept. of Information and Computer Science, Helsinki University of
More informationIntroduction to visual computation and the primate visual system
Introduction to visual computation and the primate visual system Problems in vision Basic facts about the visual system Mathematical models for early vision Marr s computational philosophy and proposal
More informationNon-linear dimension reduction
Sta306b May 23, 2011 Dimension Reduction: 1 Non-linear dimension reduction ISOMAP: Tenenbaum, de Silva & Langford (2000) Local linear embedding: Roweis & Saul (2000) Local MDS: Chen (2006) all three methods
More informationRecursive ICA. Abstract
Recursive ICA Honghao Shan, Lingyun Zhang, Garrison W. Cottrell Department of Computer Science and Engineering University of California, San Diego La Jolla, CA 92093-0404 {hshan,lingyun,gary}@cs.ucsd.edu
More informationEstimating Markov Random Field Potentials for Natural Images
Estimating Markov Random Field Potentials for Natural Images Urs Köster 1,2, Jussi T. Lindgren 1,2 and Aapo Hyvärinen 1,2,3 1 Department of Computer Science, University of Helsinki, Finland 2 Helsinki
More informationEstimating Dependency Structures for non-gaussian Components with Linear and Energy Correlations
Estimating Dependency Structures for non-gaussian Components with Linear and Energy Correlations Hiroaki Sasaki 1 hsasaki@cc.uec.ac.jp Michael U. Gutmann michael.gutmann@helsinki.fi Hayaru Shouno 1 shouno@uec.ac.jp
More informationLearning Intermediate-Level Representations of Form and Motion from Natural Movies
1 Learning Intermediate-Level Representations of Form and Motion from Natural Movies Charles F. Cadieu and Bruno A. Olshausen Redwood Center for Theoretical Neuroscience, Helen Wills Neuroscience Institute,
More informationTime Series Prediction as a Problem of Missing Values: Application to ESTSP2007 and NN3 Competition Benchmarks
Series Prediction as a Problem of Missing Values: Application to ESTSP7 and NN3 Competition Benchmarks Antti Sorjamaa and Amaury Lendasse Abstract In this paper, time series prediction is considered as
More informationFitting Models to Distributed Representations of Vision
Fitting Models to Distributed Representations of Vision Sourabh A. Niyogi Department of Electrical Engineering and Computer Science MIT Media Laboratory, 20 Ames Street, Cambridge, MA 02139 Abstract Many
More informationNCC 2009, January 16-18, IIT Guwahati 267
NCC 2009, January 6-8, IIT Guwahati 267 Unsupervised texture segmentation based on Hadamard transform Tathagata Ray, Pranab Kumar Dutta Department Of Electrical Engineering Indian Institute of Technology
More informationDifferential Structure in non-linear Image Embedding Functions
Differential Structure in non-linear Image Embedding Functions Robert Pless Department of Computer Science, Washington University in St. Louis pless@cse.wustl.edu Abstract Many natural image sets are samples
More informationLearning a Manifold as an Atlas Supplementary Material
Learning a Manifold as an Atlas Supplementary Material Nikolaos Pitelis Chris Russell School of EECS, Queen Mary, University of London [nikolaos.pitelis,chrisr,lourdes]@eecs.qmul.ac.uk Lourdes Agapito
More informationSparse coding in practice
Sparse coding in practice Chakra Chennubhotla & Allan Jepson Department of Computer Science University of Toronto, 6 King s College Road Toronto, ON M5S 3H5, Canada Email: chakra,jepson @cs.toronto.edu
More informationSimple Method for High-Performance Digit Recognition Based on Sparse Coding
1 Simple Method for High-Performance Digit Recognition Based on Sparse Coding Kai Labusch Institute for Neuro- and Bioinformatics University of Lübeck D-23538 Lübeck labusch@inb.uni-luebeck.de Erhardt
More informationEMERGENCE OF SIMPLE-CELL RECEPTIVE PROPERTIES BY LEARNING A SPARSE CODE FOR NATURAL IMAGES
EMERGENCE OF SIMPLE-CELL RECEPTIVE PROPERTIES BY LEARNING A SPARSE CODE FOR NATURAL IMAGES Bruno A. Olshausen & David J. Field Presenter: Ozgur Yigit Balkan Outline Linear data representations Sparse Vector
More informationReconstructing visual experiences from brain activity evoked by natural movies
Reconstructing visual experiences from brain activity evoked by natural movies Shinji Nishimoto, An T. Vu, Thomas Naselaris, Yuval Benjamini, Bin Yu, and Jack L. Gallant, Current Biology, 2011 -Yi Gao,
More informationTransferring Colours to Grayscale Images by Locally Linear Embedding
Transferring Colours to Grayscale Images by Locally Linear Embedding Jun Li, Pengwei Hao Department of Computer Science, Queen Mary, University of London Mile End, London, E1 4NS {junjy, phao}@dcs.qmul.ac.uk
More informationA two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images
Vision Research 41 (2001) 2413 2423 www.elsevier.com/locate/visres A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images Aapo Hyvärinen a,b,
More informationThe "tree-dependent components" of natural scenes are edge filters
The "tree-dependent components" of natural scenes are edge filters Daniel Zoran Interdisciplinary Center for Neural Computation Hebrew University of Jerusalem daniez@cs.huji.ac.il Yair Weiss School of
More informationUnsupervised Discovery of Non-Linear Structure using Contrastive Backpropagation
Unsupervised Discovery of Non-Linear Structure using Contrastive Backpropagation G. E. Hinton, S. Osindero, M. Welling and Y. W. Teh Department of Computer Science University of Toronto Toronto, Canada
More informationDominant plane detection using optical flow and Independent Component Analysis
Dominant plane detection using optical flow and Independent Component Analysis Naoya OHNISHI 1 and Atsushi IMIYA 2 1 School of Science and Technology, Chiba University, Japan Yayoicho 1-33, Inage-ku, 263-8522,
More informationLearning-based Methods in Vision
Learning-based Methods in Vision 16-824 Sparsity and Deep Learning Motivation Multitude of hand-designed features currently in use in vision - SIFT, HoG, LBP, MSER, etc. Even the best approaches, just
More informationOn spatio-temporal sparse coding: Analysis and an algorithm
On spatio-temporal sparse coding: Analysis and an algorithm Roland Memisevic Department of Computer Science University of Frankfurt ro@cs.uni-frankfurt.de Abstract Sparse coding is a common approach to
More informationNonlinear Image Interpolation using Manifold Learning
Nonlinear Image Interpolation using Manifold Learning Christoph Bregler Computer Science Division University of California Berkeley, CA 94720 bregler@cs.berkeley.edu Stephen M. Omohundro'" Int. Computer
More informationCourse Evaluations. h"p:// 4 Random Individuals will win an ATI Radeon tm HD2900XT
Course Evaluations h"p://www.siggraph.org/courses_evalua4on 4 Random Individuals will win an ATI Radeon tm HD2900XT A Gentle Introduction to Bilateral Filtering and its Applications From Gaussian blur
More informationManifold Learning for Video-to-Video Face Recognition
Manifold Learning for Video-to-Video Face Recognition Abstract. We look in this work at the problem of video-based face recognition in which both training and test sets are video sequences, and propose
More informationSupervised vs.unsupervised Learning
Supervised vs.unsupervised Learning In supervised learning we train algorithms with predefined concepts and functions based on labeled data D = { ( x, y ) x X, y {yes,no}. In unsupervised learning we are
More informationFacial Expression Classification with Random Filters Feature Extraction
Facial Expression Classification with Random Filters Feature Extraction Mengye Ren Facial Monkey mren@cs.toronto.edu Zhi Hao Luo It s Me lzh@cs.toronto.edu I. ABSTRACT In our work, we attempted to tackle
More informationConjectures regarding the nonlinear geometry of visual neurons
Conjectures regarding the nonlinear geometry of visual neurons James R. Golden a, Kedarnath P. Vilankar a, Michael C.K. Wu b,c, David J. Field a a Department of Psychology, Cornell University, Ithaca,
More informationLearning Spatio-temporally Invariant Representations from Video
Learning Spatio-temporally Invariant Representations from Video Jae Hyun Lim, Hansol Choi, Jun-Cheol Park, Jae Young Jun and Dae-shik Kim Department of Electrical Engineering Korea Advanced Institute of
More informationMöbius Transformations in Scientific Computing. David Eppstein
Möbius Transformations in Scientific Computing David Eppstein Univ. of California, Irvine School of Information and Computer Science (including joint work with Marshall Bern from WADS 01 and SODA 03) Outline
More informationCHAPTER 9 INPAINTING USING SPARSE REPRESENTATION AND INVERSE DCT
CHAPTER 9 INPAINTING USING SPARSE REPRESENTATION AND INVERSE DCT 9.1 Introduction In the previous chapters the inpainting was considered as an iterative algorithm. PDE based method uses iterations to converge
More informationCompressive Sensing for High-Dimensional Data
Compressive Sensing for High-Dimensional Data Richard Baraniuk Rice University dsp.rice.edu/cs DIMACS Workshop on Recent Advances in Mathematics and Information Sciences for Analysis and Understanding
More informationLecture 2: Spatial And-Or graph
Lecture 2: Spatial And-Or graph for representing the scene-object-part-primitive hierarchy Song-Chun Zhu Center for Vision, Cognition, Learning and Arts University of California, Los Angeles At CVPR, Providence,
More informationLearning transport operators for image manifolds
Learning transport operators for image manifolds Benjamin J. Culpepper Department of EECS Computer Science Division University of California, Berkeley Berkeley, CA 9472 bjc@cs.berkeley.edu Bruno A. Olshausen
More informationLearning Feature Hierarchies for Object Recognition
Learning Feature Hierarchies for Object Recognition Koray Kavukcuoglu Computer Science Department Courant Institute of Mathematical Sciences New York University Marc Aurelio Ranzato, Kevin Jarrett, Pierre
More informationA Quantitative Approach for Textural Image Segmentation with Median Filter
International Journal of Advancements in Research & Technology, Volume 2, Issue 4, April-2013 1 179 A Quantitative Approach for Textural Image Segmentation with Median Filter Dr. D. Pugazhenthi 1, Priya
More informationCoupling of Evolution and Learning to Optimize a Hierarchical Object Recognition Model
Coupling of Evolution and Learning to Optimize a Hierarchical Object Recognition Model Georg Schneider, Heiko Wersing, Bernhard Sendhoff, and Edgar Körner Honda Research Institute Europe GmbH Carl-Legien-Strasse
More informationCompressive Sensing. A New Framework for Sparse Signal Acquisition and Processing. Richard Baraniuk. Rice University
Compressive Sensing A New Framework for Sparse Signal Acquisition and Processing Richard Baraniuk Rice University Better, Stronger, Faster Accelerating Data Deluge 1250 billion gigabytes generated in 2010
More informationImage Restoration and Background Separation Using Sparse Representation Framework
Image Restoration and Background Separation Using Sparse Representation Framework Liu, Shikun Abstract In this paper, we introduce patch-based PCA denoising and k-svd dictionary learning method for the
More informationP257 Transform-domain Sparsity Regularization in Reconstruction of Channelized Facies
P257 Transform-domain Sparsity Regularization in Reconstruction of Channelized Facies. azemi* (University of Alberta) & H.R. Siahkoohi (University of Tehran) SUMMARY Petrophysical reservoir properties,
More informationFRESH - An algorithm for resolution enhancement of piecewise smooth signals and images
FRESH - An algorithm for resolution enhancement of piecewise smooth signals and images Imperial College London April 11, 2017 1 1 This research is supported by European Research Council ERC, project 277800
More informationFace Cyclographs for Recognition
Face Cyclographs for Recognition Guodong Guo Department of Computer Science North Carolina Central University E-mail: gdguo@nccu.edu Charles R. Dyer Computer Sciences Department University of Wisconsin-Madison
More informationThe Effect of Facial Components Decomposition on Face Tracking
The Effect of Facial Components Decomposition on Face Tracking Vikas Choudhary, Sergey Tulyakov and Venu Govindaraju Center for Unified Biometrics and Sensors, University at Buffalo, State University of
More informationMTTTS17 Dimensionality Reduction and Visualization. Spring 2018 Jaakko Peltonen. Lecture 11: Neighbor Embedding Methods continued
MTTTS17 Dimensionality Reduction and Visualization Spring 2018 Jaakko Peltonen Lecture 11: Neighbor Embedding Methods continued This Lecture Neighbor embedding by generative modeling Some supervised neighbor
More informationHeat Kernel Based Local Binary Pattern for Face Representation
JOURNAL OF LATEX CLASS FILES 1 Heat Kernel Based Local Binary Pattern for Face Representation Xi Li, Weiming Hu, Zhongfei Zhang, Hanzi Wang Abstract Face classification has recently become a very hot research
More informationLocating ego-centers in depth for hippocampal place cells
204 5th Joint Symposium on Neural Computation Proceedings UCSD (1998) Locating ego-centers in depth for hippocampal place cells Kechen Zhang,' Terrence J. Sejeowski112 & Bruce L. ~cnau~hton~ 'Howard Hughes
More informationComputational Perception. Visual Coding 3
Computational Perception 15-485/785 February 21, 2008 Visual Coding 3 A gap in the theory? - - + - - from Hubel, 1995 2 Eye anatomy from Hubel, 1995 Photoreceptors: rods (night vision) and cones (day vision)
More informationA New Multi Fractal Dimension Method for Face Recognition with Fewer Features under Expression Variations
A New Multi Fractal Dimension Method for Face Recognition with Fewer Features under Expression Variations Maksud Ahamad Assistant Professor, Computer Science & Engineering Department, Ideal Institute of
More informationTopological estimation using witness complexes. Vin de Silva, Stanford University
Topological estimation using witness complexes, Acknowledgements Gunnar Carlsson (Mathematics, Stanford) principal collaborator Afra Zomorodian (CS/Robotics, Stanford) persistent homology software Josh
More informationSparsity Based Regularization
9.520: Statistical Learning Theory and Applications March 8th, 200 Sparsity Based Regularization Lecturer: Lorenzo Rosasco Scribe: Ioannis Gkioulekas Introduction In previous lectures, we saw how regularization
More informationEnhanced Active Shape Models with Global Texture Constraints for Image Analysis
Enhanced Active Shape Models with Global Texture Constraints for Image Analysis Shiguang Shan, Wen Gao, Wei Wang, Debin Zhao, Baocai Yin Institute of Computing Technology, Chinese Academy of Sciences,
More informationLearning based face hallucination techniques: A survey
Vol. 3 (2014-15) pp. 37-45. : A survey Premitha Premnath K Department of Computer Science & Engineering Vidya Academy of Science & Technology Thrissur - 680501, Kerala, India (email: premithakpnath@gmail.com)
More informationRobust Pose Estimation using the SwissRanger SR-3000 Camera
Robust Pose Estimation using the SwissRanger SR- Camera Sigurjón Árni Guðmundsson, Rasmus Larsen and Bjarne K. Ersbøll Technical University of Denmark, Informatics and Mathematical Modelling. Building,
More informationEECS 556 Image Processing W 09. Interpolation. Interpolation techniques B splines
EECS 556 Image Processing W 09 Interpolation Interpolation techniques B splines What is image processing? Image processing is the application of 2D signal processing methods to images Image representation
More informationTechnical Report. Title: Manifold learning and Random Projections for multi-view object recognition
Technical Report Title: Manifold learning and Random Projections for multi-view object recognition Authors: Grigorios Tsagkatakis 1 and Andreas Savakis 2 1 Center for Imaging Science, Rochester Institute
More informationEdge and Texture. CS 554 Computer Vision Pinar Duygulu Bilkent University
Edge and Texture CS 554 Computer Vision Pinar Duygulu Bilkent University Filters for features Previously, thinking of filtering as a way to remove or reduce noise Now, consider how filters will allow us
More informationA Topography-Preserving Latent Variable Model with Learning Metrics
A Topography-Preserving Latent Variable Model with Learning Metrics Samuel Kaski and Janne Sinkkonen Helsinki University of Technology Neural Networks Research Centre P.O. Box 5400, FIN-02015 HUT, Finland
More informationWavelet Applications. Texture analysis&synthesis. Gloria Menegaz 1
Wavelet Applications Texture analysis&synthesis Gloria Menegaz 1 Wavelet based IP Compression and Coding The good approximation properties of wavelets allow to represent reasonably smooth signals with
More informationINDEPENDENT COMPONENT ANALYSIS WITH FEATURE SELECTIVE FILTERING
INDEPENDENT COMPONENT ANALYSIS WITH FEATURE SELECTIVE FILTERING Yi-Ou Li 1, Tülay Adalı 1, and Vince D. Calhoun 2,3 1 Department of Computer Science and Electrical Engineering University of Maryland Baltimore
More informationNon-negative Matrix Factorization with Sparseness Constraints
Journal of Machine Learning Research 5 (2004) 1457 1469 Submitted 8/04; Published 11/04 Non-negative Matrix Factorization with Sparseness Constraints Patrik O. Hoyer HIIT Basic Research Unit Department
More informationCompressive Sensing for Multimedia. Communications in Wireless Sensor Networks
Compressive Sensing for Multimedia 1 Communications in Wireless Sensor Networks Wael Barakat & Rabih Saliba MDDSP Project Final Report Prof. Brian L. Evans May 9, 2008 Abstract Compressive Sensing is an
More informationA Computational Approach To Understanding The Response Properties Of Cells In The Visual System
A Computational Approach To Understanding The Response Properties Of Cells In The Visual System David C. Noelle Assistant Professor of Computer Science and Psychology Vanderbilt University March 3, 2004
More informationFace Recognition Based On Granular Computing Approach and Hybrid Spatial Features
Face Recognition Based On Granular Computing Approach and Hybrid Spatial Features S.Sankara vadivu 1, K. Aravind Kumar 2 Final Year Student of M.E, Department of Computer Science and Engineering, Manonmaniam
More informationLecture 6 Geometric Transformations and Image Registration. Lin ZHANG, PhD School of Software Engineering Tongji University Spring 2013
Lecture 6 Geometric Transformations and Image Registration Lin ZHANG, PhD School of Software Engineering Tongji University Spring 2013 Contents Transforming points Hierarchy of geometric transformations
More informationIndependent component analysis applied to feature extraction from colour and stereo images
Network: Comput. Neural Syst. 11 (2000) 191 210. Printed in the UK PII: S0954-898X(00)14814-6 Independent component analysis applied to feature extraction from colour and stereo images Patrik O Hoyer and
More informationFace Modeling by Information Maximization 1
Face Modeling by Information Maximization 1 Marian Stewart Bartlett Javier R. Movellan Terrence J. Sejnowski UC San Diego UC San Diego UC San Diego; Salk marni@salk.edu movellan@mplab.ucsd.edu Howard Hughes
More informationMotion Estimation. There are three main types (or applications) of motion estimation:
Members: D91922016 朱威達 R93922010 林聖凱 R93922044 謝俊瑋 Motion Estimation There are three main types (or applications) of motion estimation: Parametric motion (image alignment) The main idea of parametric motion
More informationChapter 7: Competitive learning, clustering, and self-organizing maps
Chapter 7: Competitive learning, clustering, and self-organizing maps António R. C. Paiva EEL 6814 Spring 2008 Outline Competitive learning Clustering Self-Organizing Maps What is competition in neural
More informationNonlinear Generative Models for Dynamic Shape and Dynamic Appearance
Nonlinear Generative Models for Dynamic Shape and Dynamic Appearance Ahmed Elgammal Department of Computer Science, Rutgers University, Piscataway, NJ, USA elgammal@cs.rutgers.edu Abstract Our objective
More informationA Modified Spline Interpolation Method for Function Reconstruction from Its Zero-Crossings
Scientific Papers, University of Latvia, 2010. Vol. 756 Computer Science and Information Technologies 207 220 P. A Modified Spline Interpolation Method for Function Reconstruction from Its Zero-Crossings
More information