HW #4. Hierarchical Temporal Memory

Size: px
Start display at page:

Download "HW #4. Hierarchical Temporal Memory"

Transcription

1 HW #4. Hierarchical Temporal Memory Implement episodic memory using an HTM network. Skeleton codes are available from Using the code, you are required to store and predict task episodes. After the learning process, confirm if the HTM can predict the next event for the following input cue: The same events learned (consecutively applied to the HTM) A first event of an episode An event in the middle of an episode An incomplete event (either an action or an object is missing) 1

2 In encoding, Discuss the advantage of using 3 bits for an object, instead of using one bit. In spatial pooling, Try with the various values of NUM_COL and NUM_ACTIVATED_COL, and find the required minimum number of NUM_COL. Discuss what happens if the SP process is skipped, i.e. Encoding Temporal pooling Decoding In temporal pooling, Try with NUM_CELL from 1 to 20 and discuss the role of cells. In anomaly detection Plot the cell status when an anomaly occurs. Explain why all the cells within the activated columns are activated. Compare the performance of HTM to that of EM (Deep) ART 2

3 Using the skeleton codes, fill the following functions in Fill folder: anomalydetection.py Submit the report along with your codes with a zip file name: HW4_yourname.zip Due date: May 9, 2017 Send to: yhyoo@rit.kaist.ac.kr 3

4 Nupic: A python library developed by Numenta, Inc., implementing HTM Installation of Nupic in Ubuntu Install python $ sudo apt-get install python-pip $ sudo apt-get install python-dev Install nupic bindings $ pip install 2.amazonaws.com/artifacts.numenta.org/numenta/nupic.core/releases/nupic.bindin gs/nupic.bindings cp27-none-linux_x86_64.whl--user Install nupic $ pip install nupic --user Export environment variable $ sudo vi /etc/bash.bashrc Register your nupic path, e.g., - export NUPIC=/home/RITL/nupic Save and quit $ source /etc/bash.bashrc Check your environment variable $ echo $NUPIC 4

5 Verification of Nupic installation Install pythest and git for testing nupic $ sudo apt-get install python-pytest $ sudo apt-get install git Download nupic example files from the server $ git clone $ cd nupic Run nupic installation tests $./scripts/run_nupic_tests u Tests should be PASSED or SKIPPED For more information on Nupic installation, 5

6 PyCharm Python IDE for developers, developed by Jetbrain, Inc. Installation of Pycharm 5 Copy the attached file pycharm-5.04.tar.gz to the desired installation location Unpack the pycharm-5.04.tar.gz using the following command: $ tar xfz pycharm-5.04.tar.gz Remove the pycharm-5.04.tar.gz to save disk space (optional) $ rm pycharm-5.04.tar.gz Run pycharm.sh from the bin directory $ cd pycharm-5.04-community/bin $./pycharm.sh For more information on installing PyCharm, 6

7 HW #?. Hierarchical Temporal Memory Matplotlib Python library for visualization Installation of matplotlib $ sudo apt-get install python-matplotlib 7

8 Episodic memory for task intelligence Episode #1: Water the flowers Episode #2: Bring a book in a drawer Episode #3: Pour the contents of a bottle Episode #4: Sort the toys Episode #5: Toast a slice of bread 8

9 HTM as an episodic memory model 9

10 HTM procedure: 1. Encoding 2. Spatial Pooling 3. Temporal Pooling 4. Decoding (for classification) 1. Encoding To change sensory data into a binary string understood by HTM. Make sure the semantics of the particular data type should be captured. Encoder types: Category: actions, objects, etc. Scalar: real numbers, indoor temperature change, etc. Coordinate: GPS log, location, etc. Date 10

11 5 task episodes Sort toys Water flowers Bring an object Toast a bread Pour the contents Action Object Action Object Action Object Action Object Action Object Grasp RS Walk to WP Walk to Drawer Grasp Bread Grasp Vinegar Move to Box_1 Bend Grasp to Handle Move to Toaster Move to Bowl Release Grasp WP Pull Put into Toaster Tilt Grasp RC Raise Release Move to Button Stand Move to Box_1 Straight Grasp Red arch Press Button Move to Table Release Walk to FP Raise Bread Grasp Release Grasp RT Move to FP Grasp Handle Move to Dish Grasp Mustard Move to Box_1 Tilt Push Release Move to Bowl Release Stand Release Squeeze Grasp GS Move to Ground Walk to Box_1 Move to Table Move to Box_2 Release Move to Box_1 Release Release Release Grasp Sesame Grasp GC Move to Bowl RS = red square, RC = red cylinder, RT = red triangle, GS = Green square, GC = Green cylinder WP = watering pot, FP = flower pot *Some part of sort toys scenario are skipped for the lack of the space of the slide Shake Move to Release Table 11

12 68 encoded inputs (total # of events) Total 138 bits for each encoded input of which element by 3 bits: 15 actions: Grasp, move to, release, tilt, stand, push, pull, put into, shake, squeeze, walk, bend, press, straight, raise. 28 objects: Red-square, re-cylinder, red-arch, red-triangle, green-triangle, green-cylinder, green-arch, green-triangle, blue-square, blue-cylinder, blue-arch, blue-triangle, watering-pot, dish, bread, handle, red-vinegar, mustard, sesame, box-1, box-2, box-3, flower pot, toaster, button, drawer, bowl, table 2 human detection information: Detected (appear), not detected (disappear) 1 end of a sequence: Completed 12

13 Examples of encoded inputs Grasp Red square : [ ] Move Box _ 1 : [ ] Release : [ ] The structure of an encoded input Actions Objects Human detection End 13

14 Code In five_scenarios.py: : output encodedinput = five_scenarios_input.input_generator_total(input_dim=input_dim) # total 68 encoded inputs In five_scenarios_input.py: def input_generator_total(input_dim): encodedinput = numpy.zeros((68, INPUT_DIM), dtype='int') encodedinput[0] = input_generator(0, 0, 99, 99) # grasp, red square, none, none encodedinput[1] = input_generator(0, 1, 99, 99) # grasp, red cylinder, none, none encodedinput[67] = input_generator(99, 99, 99, 1) # none, none, none, finish return encodedinput def input_generator(val_1, val_2, val_3, val_4): ''' Generate HTM inputs (binary vectors) given four kinds of symbols. Parameters val_1 : Action type ( grasp, move, release ) from 0 to 14 val_2 : Object type ( red square, red cylinder, table ) from 0 to 27 val_3 : Human type ( disappear, appear ) 0 and 1 val_4 : End type ( finish ) 0 Returns encoded binary vector ''' 14

15 2. Spatial pooling To change input into sparse distributed representation (SDR). The dimension of SDR equals the column dimension of the HTM. In this homework, the dimension of SDR = 200 (NUM_COL) 10 columns (NUM_ACTIVATED_COL) are activated out of Inputs Spatial pooler results (binary string) (represented as the indices of the activated columns) Grasp, Red square [40, 92, 168, 172, 178, 181, 182, 183, 184, 187] Grasp, Red cylinder [16, 20, 27, 68, 85, 114, 126, 174, 177, 178] Grasp, Red arch [27, 55, 90, 100, 140, 177, 182, 186, 187, 193] 15

16 : output Code In five_scenarios.py # Initialize spatial pooler sp = SpatialPooler(inputDimensions=(INPUT_DIM,), columndimensions=(num_col,), potentialradius=120, numactivecolumnsperinharea=active_bit, globalinhibition=true, synpermactiveinc=0.04, potentialpct=1.0) # Start Learning SP SP_output = numpy.zeros((len(encodedinput), NUM_COL), dtype="int") for i in range(sp_iter): # repeat 200 times for j in range(len(encodedinput)): sp.compute(encodedinput[j], learn=true, activearray=sp_output[j]) 16

17 3. Temporal pooling Core part of HTM To change the SDR (the pattern of the activation of the columns) into a pattern of activation of cells, and Also to make a prediction through a pattern of predicted cells. A pattern of predicted cells represents a prediction of a next-coming input. In this homework, the number of cells per a columns = 20 (NUM_CELL) 17

18 Code In five_scenarios.py # Initialize temporal pooler tp = TP(numberOfCols=NUM_COL, cellspercolumn=num_cell, initialperm=0.5, connectedperm=0.5, minthreshold=5, newsynapsecount=10, permanenceinc=0.05, permanencedec=0.01, activationthreshold=5, globaldecay=0.01, burnin=1, checksynapseconsistency=false, pamlength=10) # Start Learning TP for i in range(tp_iter): # learning for 40 times # Through temporal pooling, HTM learns the temporal sequence of spatial patterns (SDR). # When a temporal sequence ends, use tp.reset() so that HTM knows that the temporal sequence has ended. # When enablelearn=true, tp learns the temporal sequence between inputs. # When computeinfoutput=true, tp infers the next-coming input through a pattern of predicted cells. ##### Sorting toys ##### tp.compute(sp_output[0], enablelearn=true, computeinfoutput=false) # grasp, red square, tp.compute(sp_output[67], enablelearn=true, computeinfoutput=false) # finish tp.reset() #### taking a contents #### tp.compute(sp_output[16], enablelearn=true, computeinfoutput=false) # grasp, red-vinegar, tp.compute(sp_output[67], enablelearn=true, computeinfoutput=false) # finish tp.reset() # Learning process is finished. Decoding is not needed during learning. 18

19 4. Decoding To decode the pattern of predicted columns, so that users can easily understand the meaning of the pattern. In this homework, decoding is implemented by the following function: five_scenarios_input.find_pattern(columns,num_col,sp_output) This function finds the meaning of Columns. The function compares the current input with all learned spatial pattern (SP_output), by counting the number of overlapping bits between the current input and a learned spatial pattern. The one with the largest number of overlapping bits is selected. 19

20 Code In five_scenarios.py : output of TP : output of decoding for t in range(1000): #This is NOT a process for learning; this is a process for Decoding. # Encodeing : get an input from a user and transform it as a form of a binary string. encodedinput_for_simulation= five_scenarios_input.input_generator_2(t, NUM_COL, INPUT_DIM) # Spatial pooling : get a encodedinput and put out the corresponding SDR (SP_output_for_simulation) sp.compute(encodedinput_for_simulation, learn=false, activearray=sp_output_for_simulation) # Temporal pooling : get a SDR and put out a pattern of predicted cells (predictedcells) tp.compute(sp_output_for_simulation, enablelearn=false, computeinfoutput=true) predictedcells = tp.getpredictedstate() # Decoding : get a pattern of predicted columns # put out the predicted next-coming input(procedural[k+1], character string) # Change the pattern of predicted cells into a pattern of predicted columns. predictedcolumns = five_scenarios_input.cells2columns(cells=predictedcells, NUM_COL=NUM_COL) # Compare the next-predicted SDR (predictedcolumns) with all previously leaned SDR patterns (SP_output) # The best-mating event becomes the output, as a form of a character string. procedural.append(five_scenarios_input.find_pattern(columns=predictedcolumns, NUM_COL=NUM_COL, SP_output=SP_output, INPUT_DIM=INPUT_DIM,encodedInput=encodedInput)[0]) 20

21 5. Anomaly detection HTM can easily detect anomalies, by comparing predicted columns at time t-1 and activated columns at time t. Anomaly score is the fraction of active columns that were not predicted. Anomaly detection is implemented by using the following equation: where Predicted columns at time 1 Active columns at time The number of columns 21

22 Code In five_scenarios.py: : output # Anomaly Detection # # except first loop (k=0), calculate anomaly value if k > 0: anomalyscore = anomalydetection.anomalyscore(activecolumns=sp_output_for_simulation, predictedcolumns=predictedcolumns) # If the anomaly score exceeds a threshold (ANOMALY_THRESHOLD=0.5) it is considered as an anomaly. if anomalyscore > ANOMALY_THRESHOLD: print "anomaly detected In Fill/anomalyDetection.py: def anomalyscore(activecolumns, predictedcolumns): # You are required to implement anomalydetection. return anomalyscore 22

23 Pseudo code of the overall HTM procedure FOR (i = 0; i<num_dataset; i++) DO : EncodedInput[i] = Encode(SensoryInput[i]); FOR (i = 0; i<num_dataset; i++) DO : SP_output[i] = SpatialPooling(EncodedInput[i], Learn=True); FOR (i = 0; i<num_dataset; i++) DO : TemporalPooling(SP_output[i], Learn=True, Prediction = False); Learning process t = 0; WHILE(TRUE) DO: oneencodedinput = Encode(SensoryInputFromUser); onesp_output = SpatialPooling(oneEncodedInput, Learn = False); onetp_output = TemporalPooling(oneSP_output, Learn = False, Prediction = True); Procedural[t+1] = Decode(oneTP_output) PRINT Next Predicted Event =, Procedural[t+1] t++; Prediction & decoding process 23

24 Results pouring the contents of a bottle scenario At 0, the first input of the scenario, (Grasp Red-vinegar) to HTM Current state: Grasp a red vinegar bottle Next predicted state: Move to a bowl 24

25 At 1, the second input of the scenario, (Move-to Bowl) to HTM Current state: Move to a bowl Next predicted state: Tilt 25

26 At 1, an unexpected input, (Move to Table) to HTM HTM is expecting (Move to Bowl ) Current state: Move to the table Next predicted state: Release 26

Artificial Intelligence Introduction Handwriting Recognition Kadir Eren Unal ( ), Jakob Heyder ( )

Artificial Intelligence Introduction Handwriting Recognition Kadir Eren Unal ( ), Jakob Heyder ( ) Structure: 1. Introduction 2. Problem 3. Neural network approach a. Architecture b. Phases of CNN c. Results 4. HTM approach a. Architecture b. Setup c. Results 5. Conclusion 1.) Introduction Artificial

More information

PYTHON. BBM103 Introduction to Programming Lab 1. Hacettepe University Computer Engineering Department

PYTHON. BBM103 Introduction to Programming Lab 1. Hacettepe University Computer Engineering Department PYTHON BBM103 Introduction to Programming Lab 1 Hacettepe University Computer Engineering Department Beytepe 2016 Installation 1. Download PyCharm Edu from https://www.jetbrains.com/pycharm-edu/download/

More information

Homework 01 : Deep learning Tutorial

Homework 01 : Deep learning Tutorial Homework 01 : Deep learning Tutorial Introduction to TensorFlow and MLP 1. Introduction You are going to install TensorFlow as a tutorial of deep learning implementation. This instruction will provide

More information

Spatial Pooler Algorithm Implementation and Pseudocode

Spatial Pooler Algorithm Implementation and Pseudocode Chapter Revision History The table notes major changes between revisions. Minor changes such as small clarifications or formatting changes are not noted. Version Date Changes Principal Author(s) 0.4 Initial

More information

Lecture 3: Processing Language Data, Git/GitHub. LING 1340/2340: Data Science for Linguists Na-Rae Han

Lecture 3: Processing Language Data, Git/GitHub. LING 1340/2340: Data Science for Linguists Na-Rae Han Lecture 3: Processing Language Data, Git/GitHub LING 1340/2340: Data Science for Linguists Na-Rae Han Objectives What do linguistic data look like? Homework 1: What did you process? How does collaborating

More information

doconv Documentation Release Jacob Mourelos

doconv Documentation Release Jacob Mourelos doconv Documentation Release 0.1.6 Jacob Mourelos October 17, 2016 Contents 1 Introduction 3 2 Features 5 2.1 Available Format Conversions...................................... 5 3 Installation 7 3.1

More information

Big Data Challenges in Large IP Networks

Big Data Challenges in Large IP Networks Big Data Challenges in Large IP Networks Feature Extraction & Predictive Alarms for network management Wednesday 28 th Feb 2018 Dave Yearling British Telecommunications plc 2017 What we will cover Making

More information

Chisel floor levels and doom3 botlib experimentation, documentation and extension

Chisel floor levels and doom3 botlib experimentation, documentation and extension slide 1 Chisel floor levels and doom3 botlib experimentation, documentation and extension for your coursework you need to alter chisel and also extend the doom3 botlib API during this tutorial we will

More information

Setting up PyCharm Professional

Setting up PyCharm Professional Page 1 Setting up PyCharm Professional You should have already done the following, per a previous document: 1. Install PyCharm Professional 2. Install Git 3. Create a Github account If you have not already

More information

CSE 101 Introduction to Computers Development / Tutorial / Lab Environment Setup

CSE 101 Introduction to Computers Development / Tutorial / Lab Environment Setup CSE 101 Introduction to Computers Development / Tutorial / Lab Environment Setup Purpose: The purpose of this lab is to setup software that you will be using throughout the term for learning about Python

More information

Numenta Node Algorithms Guide NuPIC 1.7

Numenta Node Algorithms Guide NuPIC 1.7 1 NuPIC 1.7 includes early implementations of the second generation of the Numenta HTM learning algorithms. These algorithms are available as two node types: SpatialPoolerNode and TemporalPoolerNode. This

More information

Extracting Rankings for Spatial Keyword Queries from GPS Data

Extracting Rankings for Spatial Keyword Queries from GPS Data Extracting Rankings for Spatial Keyword Queries from GPS Data Ilkcan Keles Christian S. Jensen Simonas Saltenis Aalborg University Outline Introduction Motivation Problem Definition Proposed Method Overview

More information

Manual of SPCI (structural and physico-chemical interpretation) open-source software version 0.1.5

Manual of SPCI (structural and physico-chemical interpretation) open-source software version 0.1.5 Manual of SPCI (structural and physico-chemical interpretation) open-source software version 0.1.5 Version (date) Changes and comments 0.1.0 (02.02.2015) Changes from alpha version: 1. More precise default

More information

datapusher Documentation

datapusher Documentation datapusher Documentation Release 1.0 Open Knowledge International July 13, 2018 Contents 1 Development installation 3 2 Production installation and Setup 5 2.1 Download and Install (All CKAN Versions)...............................

More information

Lab 1: Cipher Fundamentals

Lab 1: Cipher Fundamentals Lab 1: Cipher Fundamentals Objective: The key objective of this lab is to be introduced to some of the fundamental principles involved in cryptography, including the usage of Base-64, hexadecimal, the

More information

Tizen TCT User Guide

Tizen TCT User Guide Tizen 2.3.1 TCT User Guide Table of Contents 1. Environment setup... 3 1.1. Symbols and abbreviations... 3 1.2. Hardware Requirements... 3 1.3. Software Requirements... 3 2. Getting TCT-source and TCT-manager...

More information

Local Music Bot Documentation

Local Music Bot Documentation Local Music Bot Documentation Release 1.0.1 Natsulus Jul 22, 2017 Getting Started 1 Installing 3 2 Config 5 3 Commands 7 4 Query 15 5 Role 17 6 Perms 21 7 Library 25 8 TODO 27 9 Changelog 29 i ii The

More information

2 Installing the Software

2 Installing the Software INSTALLING 19 2 Installing the Software 2.1 Installation Remember the hour or two of slogging through software installation I promised (or warned) you about in the introduction? Well, it s here. Unless

More information

Geocoding Sentinel-1 GRD Products using GDAL Utilities

Geocoding Sentinel-1 GRD Products using GDAL Utilities Geocoding Sentinel-1 GRD Products using GDAL Utilities Adapted from coursework developed by Franz J Meyer, Ph.D., Alaska Satellite Facility. GDAL installation adapted from UCLA s Technology Sandbox website

More information

DEVELOPMENT GUIDE VAB-630. Linux BSP v

DEVELOPMENT GUIDE VAB-630. Linux BSP v DEVELOPMENT GUIDE VAB-630 Linux BSP v1.0.1 100-09182017-114400 Copyright Copyright 2017 VIA Technologies Incorporated. All rights reserved. No part of this document may be reproduced, transmitted, transcribed,

More information

Getting started with Python

Getting started with Python Getting started with Python (i.e. installing and testing it) 2018 From original slides by Tony Cahill What is Python? Python is a free computer language that was created in 1991 It has many add-ons (called

More information

Neural Network Compiler BNN Scripts User Guide

Neural Network Compiler BNN Scripts User Guide FPGA-UG-02055 Version 1.0 May 2018 Contents 1. Introduction... 3 2. Software Requirements... 3 3. Directory Structure... 3 4. Installation Guide... 4 4.1. Installing Dependencies... 4 4.2. Installing Packages...

More information

Systems Programming and Computer Architecture ( ) Exercise Session 01 Data Lab

Systems Programming and Computer Architecture ( ) Exercise Session 01 Data Lab Systems Programming and Computer Architecture (252-0061-00) Exercise Session 01 Data Lab 1 Goal Get familiar with bit level representations, C and Linux Thursday, September 22, 2016 Systems Programming

More information

Yocto Project internal tools

Yocto Project internal tools Lecture 5 5 Yocto Project internal tools 08 noiembrie 2016 Outline Hob Toaster Autobuilder Devtool 08.11.2016 2 Recap: ADT Application Development Toolkit Optional Eclipse Yocto plug-ins available Qemu

More information

HESP PIPELINE v. 1.0

HESP PIPELINE v. 1.0 HESP PIPELINE v. 1.0 Installation and Usage Arun Surya 20/06/2017 1. INSTALLATION The HESP pipeline installation zip file can be downloaded from, https://www.iiap.res.in/hesp/hesp_pipeline.zip. The zip

More information

Homework #4 Programming Assignment Due: 11:59 pm, November 4, 2018

Homework #4 Programming Assignment Due: 11:59 pm, November 4, 2018 CSCI 567, Fall 18 Haipeng Luo Homework #4 Programming Assignment Due: 11:59 pm, ovember 4, 2018 General instructions Your repository will have now a directory P4/. Please do not change the name of this

More information

EE368 Project: Visual Code Marker Detection

EE368 Project: Visual Code Marker Detection EE368 Project: Visual Code Marker Detection Kahye Song Group Number: 42 Email: kahye@stanford.edu Abstract A visual marker detection algorithm has been implemented and tested with twelve training images.

More information

ModBot Software Documentation 4CAD April 30, 2018

ModBot Software Documentation 4CAD April 30, 2018 Password to the Raspberry Pi: 4cadinc ModBot Software Documentation 4CAD April 30, 2018 Main Installations In Pi BIOS, enable i2c and camera Ruby Version Manager (downloadable at rvm.io) MySQL server and

More information

swiftenv Documentation

swiftenv Documentation swiftenv Documentation Release 1.3.0 Kyle Fuller Sep 27, 2017 Contents 1 The User Guide 3 1.1 Installation................................................ 3 1.2 Getting Started..............................................

More information

Kaggle See Click Fix Model Description

Kaggle See Click Fix Model Description Kaggle See Click Fix Model Description BY: Miroslaw Horbal & Bryan Gregory LOCATION: Waterloo, Ont, Canada & Dallas, TX CONTACT : miroslaw@gmail.com & bryan.gregory1@gmail.com CONTEST: See Click Predict

More information

halef Documentation ETS

halef Documentation ETS ETS Apr 02, 2018 Contents 1 OpenVXML Without Tears 1 2 Halef Setup Process 19 i ii CHAPTER 1 OpenVXML Without Tears 1 Authors Vikram Ramanarayanan and Eugene Tsuprun (with inputs from the OpenVXML Setup

More information

Tensorflow v0.10 installed from scratch on Ubuntu 16.04, CUDA 8.0RC+Patch, cudnn v5.1 with a 1080GTX

Tensorflow v0.10 installed from scratch on Ubuntu 16.04, CUDA 8.0RC+Patch, cudnn v5.1 with a 1080GTX Tensorflow v0.10 installed from scratch on Ubuntu 16.04, CUDA 8.0RC+Patch, cudnn v5.1 with a 1080GTX While Tensorflow has a great documentation, you have quite a lot of details that are not obvious, especially

More information

Unix - Basics Course on Unix and Genomic Data Prague, January 2017

Unix - Basics Course on Unix and Genomic Data Prague, January 2017 Unix - Basics Course on Unix and Genomic Data Prague, January 2017 Libor Mořkovský, Václav Janoušek, Anastassiya Zidkova, Anna Přistoupilová, Filip Sedlák http://ngs-course.readthedocs.org/en/praha-january-2017/

More information

Motion in 2D image sequences

Motion in 2D image sequences Motion in 2D image sequences Definitely used in human vision Object detection and tracking Navigation and obstacle avoidance Analysis of actions or activities Segmentation and understanding of video sequences

More information

AMath 483/583 Lecture 2

AMath 483/583 Lecture 2 AMath 483/583 Lecture 2 Outline: Binary storage, floating point numbers Version control main ideas Client-server version control, e.g., CVS, Subversion Distributed version control, e.g., git, Mercurial

More information

Zephyr Kernel Installation & Setup Manual

Zephyr Kernel Installation & Setup Manual Zephyr Kernel Installation & Setup Manual Zephyr kernel is a small footprint Single address space OS, i.e, it combines application specific code with a custom kernel to create a monolithic image that gets

More information

CS234 Azure Step-by-Step Setup

CS234 Azure Step-by-Step Setup CS234 Azure Step-by-Step Setup Adapted from the setup instructions for Chris Manning s 2017 offering of CS224n Key-Points This guide will walk you through running your code on GPUs in Azure. Before we

More information

TangeloHub Documentation

TangeloHub Documentation TangeloHub Documentation Release None Kitware, Inc. September 21, 2015 Contents 1 User s Guide 3 1.1 Managing Data.............................................. 3 1.2 Running an Analysis...........................................

More information

CS 2223 B15 Term. Homework 1 (100 pts.)

CS 2223 B15 Term. Homework 1 (100 pts.) CS 2223 B15 Term. Homework 1 (100 pts.) Homework Instructions This homework is to be completed individually. If you have any questions as to what constitutes improper behavior, review the examples I have

More information

mltool Documentation Release Maurizio Sambati

mltool Documentation Release Maurizio Sambati mltool Documentation Release 0.5.1 Maurizio Sambati November 18, 2015 Contents 1 Overview 3 1.1 Features.................................................. 3 1.2 Installation................................................

More information

Archan. Release 2.0.1

Archan. Release 2.0.1 Archan Release 2.0.1 Jul 30, 2018 Contents 1 Archan 1 1.1 Features.................................................. 1 1.2 Installation................................................ 1 1.3 Documentation..............................................

More information

GIT. A free and open source distributed version control system. User Guide. January, Department of Computer Science and Engineering

GIT. A free and open source distributed version control system. User Guide. January, Department of Computer Science and Engineering GIT A free and open source distributed version control system User Guide January, 2018 Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur Table of Contents What is

More information

AMath 483/583 Lecture 2. Notes: Notes: Homework #1. Class Virtual Machine. Notes: Outline:

AMath 483/583 Lecture 2. Notes: Notes: Homework #1. Class Virtual Machine. Notes: Outline: AMath 483/583 Lecture 2 Outline: Binary storage, floating point numbers Version control main ideas Client-server version control, e.g., CVS, Subversion Distributed version control, e.g., git, Mercurial

More information

coxtactoe Documentation

coxtactoe Documentation coxtactoe Documentation Release 0.1.0 Brett Anderson July 13, 2014 Contents 1 Contents 1 1.1 Pre-requisites............................................... 1 1.2 Installation & Configuration.......................................

More information

Frontier Documentation

Frontier Documentation Frontier Documentation Release 0.1.3-dev Sam Nicholls August 14, 2014 Contents 1 Frontier 3 1.1 Requirements............................................... 3 1.2 Installation................................................

More information

MAGPIE Installation Guide (version 1.0)

MAGPIE Installation Guide (version 1.0) MAGPIE Installation Guide (version 1.0) June 2017 Authors: Sophiane Senni, Pierre-Yves Péneau, Abdoulaye Gamatié 1 Contents 1 About this guide 3 2 Framework installation 4 2.1 Dependencies...................................

More information

Pypeline Documentation

Pypeline Documentation Pypeline Documentation Release 0.2 Kyle Corbitt May 09, 2014 Contents 1 Contents 3 1.1 Installation................................................ 3 1.2 Quick Start................................................

More information

Swarming in NuPIC. September 6, 2013

Swarming in NuPIC. September 6, 2013 Swarming in NuPIC September 6, 2013 What swarming does Automatically determines the best CLA model for a given dataset Determines which components should go into the model (encoders, spatial & temporal

More information

Homework for Section 5.1

Homework for Section 5.1 Homework for Section 5.1 1. reate the rotation R(T) 2. reate the reflection F(T) of the triangle T shown below 90 degrees of the triangle T shown below across clockwise about the center point of rotation.

More information

Valkyrie Detectors Tutorial

Valkyrie Detectors Tutorial Valkyrie Detectors Tutorial Contents 1. Valkyrie Academia... 3 2. Precise Detectors... 3 2.1. Precise Detector Types... 3 2.2. Supported File Types... 4 3. Custom Precise Detector Implementation... 4 3.1.

More information

CLC Server. End User USER MANUAL

CLC Server. End User USER MANUAL CLC Server End User USER MANUAL Manual for CLC Server 10.0.1 Windows, macos and Linux March 8, 2018 This software is for research purposes only. QIAGEN Aarhus Silkeborgvej 2 Prismet DK-8000 Aarhus C Denmark

More information

TENSORRT 4.0 RELEASE CANDIDATE (RC)

TENSORRT 4.0 RELEASE CANDIDATE (RC) TENSORRT 4.0 RELEASE CANDIDATE (RC) DU-08731-001_v4.0 RC March 2018 Installation Guide TABLE OF CONTENTS Chapter 1. Overview... 1 Chapter 2. Getting Started... 2 Chapter 3. Downloading TensorRT...3 Chapter

More information

Python simple arp table reader Documentation

Python simple arp table reader Documentation Python simple arp table reader Documentation Release 0.0.1 David Francos Nov 17, 2017 Contents 1 Python simple arp table reader 3 1.1 Features.................................................. 3 1.2 Usage...................................................

More information

pytest-benchmark Release 2.5.0

pytest-benchmark Release 2.5.0 pytest-benchmark Release 2.5.0 September 13, 2015 Contents 1 Overview 3 1.1 pytest-benchmark............................................ 3 2 Installation 7 3 Usage 9 4 Reference 11 4.1 pytest_benchmark............................................

More information

Platform Migrator Technical Report TR

Platform Migrator Technical Report TR Platform Migrator Technical Report TR2018-990 Munir Contractor mmc691@nyu.edu Christophe Pradal christophe.pradal@inria.fr Dennis Shasha shasha@cs.nyu.edu May 12, 2018 CONTENTS: 1 Abstract 4 2 Platform

More information

143a, Spring 2018 Discussion Week 4 Programming Assignment. Jia Chen 27 Apr 2018

143a, Spring 2018 Discussion Week 4 Programming Assignment. Jia Chen 27 Apr 2018 143a, Spring 2018 Discussion Week 4 Programming Assignment Jia Chen 27 Apr 2018 Annoucements HW2 posted due Friday, May 4, 2018, 11:55 PM Programming Assignment posted due Friday, Jun 1, 2018, 11:55 PM

More information

GUT. GUT Installation Guide

GUT. GUT Installation Guide Date : 02 Feb 2009 1/5 GUT Table of Contents 1 Introduction...2 2 Installing GUT...2 2.1 Optional Extensions...2 2.2 Installing from source...2 2.3 Installing the Linux binary package...4 2.4 Installing

More information

UI cases Documentation

UI cases Documentation UI cases Documentation Release 0.0.1a Sergei Chipiga Nov 03, 2016 Contents 1 Task to resolve 1 2 Solution 3 2.1 Autotests for top 250 IMDB movies................................... 5 Python Module Index

More information

wordclock_for_rpi Documentation

wordclock_for_rpi Documentation wordclock_for_rpi Documentation Release 0.0.1 Bernd Krolla Oct 25, 2017 Contents 1 General considerations 1 1.1 If you want to build a wordclock..................................... 1 2 Hardware setup

More information

A NOVEL FPGA IMPLEMENTATION OF HIERARCHICAL TEMPORAL MEMORY SPATIAL POOLER. Paul Jeffrey Mitchell. A thesis. submitted in partial fulfillment

A NOVEL FPGA IMPLEMENTATION OF HIERARCHICAL TEMPORAL MEMORY SPATIAL POOLER. Paul Jeffrey Mitchell. A thesis. submitted in partial fulfillment A NOVEL FPGA IMPLEMENTATION OF HIERARCHICAL TEMPORAL MEMORY SPATIAL POOLER by Paul Jeffrey Mitchell A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in

More information

Pymixup Documentation

Pymixup Documentation Pymixup Documentation Release 1.0.2 Richard DeVost June 09, 2016 Contents 1 Why Obfuscate? 3 2 What pymixup Does 5 3 Contents 7 3.1 Installation................................................ 7 3.2 Program

More information

EE516: Embedded Software Project 1. Setting Up Environment for Projects

EE516: Embedded Software Project 1. Setting Up Environment for Projects EE516: Embedded Software Project 1. Setting Up Environment for Projects By Dong Jae Shin 2015. 09. 01. Contents Introduction to Projects of EE516 Tasks Setting Up Environment Virtual Machine Environment

More information

ViTraM: VIsualization of TRAnscriptional Modules

ViTraM: VIsualization of TRAnscriptional Modules ViTraM: VIsualization of TRAnscriptional Modules Version 1.0 June 1st, 2009 Hong Sun, Karen Lemmens, Tim Van den Bulcke, Kristof Engelen, Bart De Moor and Kathleen Marchal KULeuven, Belgium 1 Contents

More information

Game Server Manager Documentation

Game Server Manager Documentation Game Server Manager Documentation Release 0.1.1+0.gc111f9c.dirty Christopher Bailey Dec 16, 2017 Contents 1 Game Server Manager 3 1.1 Requirements............................................... 3 1.2

More information

1. AREAS. Geometry 199. A. Rectangle = base altitude = bh. B. Parallelogram = base altitude = bh. C. Rhombus = 1 product of the diagonals = 1 dd

1. AREAS. Geometry 199. A. Rectangle = base altitude = bh. B. Parallelogram = base altitude = bh. C. Rhombus = 1 product of the diagonals = 1 dd Geometry 199 1. AREAS A. Rectangle = base altitude = bh Area = 40 B. Parallelogram = base altitude = bh Area = 40 Notice that the altitude is different from the side. It is always shorter than the second

More information

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN Background Related Work Architecture Experiment Mask R-CNN Background Related Work Architecture Experiment Background From left

More information

Homework 3. Theory (50 points) Data Structures and Algorithms in JAVA Shlomo Hershkop Department of Computer Science Columbia University Summer 2002

Homework 3. Theory (50 points) Data Structures and Algorithms in JAVA Shlomo Hershkop Department of Computer Science Columbia University Summer 2002 Homework 3 Data Structures and Algorithms in JAVA Shlomo Hershkop Department of Computer Science Columbia University Summer 2002 Due Thursday, Aug 1 (at beginning of class) Theory (50 points) 1. (5 points)

More information

Movidius Neural Compute Stick

Movidius Neural Compute Stick Movidius Neural Compute Stick You may not use or facilitate the use of this document in connection with any infringement or other legal analysis concerning Intel products described herein. You agree to

More information

ACM INTERNATIONAL COLLEGIATE PROGRAMMING CONTEST. California State University, Sacramento s. Contestant s Guide

ACM INTERNATIONAL COLLEGIATE PROGRAMMING CONTEST. California State University, Sacramento s. Contestant s Guide ACM INTERNATIONAL COLLEGIATE PROGRAMMING CONTEST California State University, Sacramento s PC 2 Contestant s Guide This guide is intended to familiarize you with the process of submitting programs to Contest

More information

Homework Assignment #3

Homework Assignment #3 CS 540-2: Introduction to Artificial Intelligence Homework Assignment #3 Assigned: Monday, February 20 Due: Saturday, March 4 Hand-In Instructions This assignment includes written problems and programming

More information

bottle-rest Release 0.5.0

bottle-rest Release 0.5.0 bottle-rest Release 0.5.0 February 18, 2017 Contents 1 API documentation 3 1.1 bottle_rest submodule.......................................... 3 2 What is it 5 2.1 REST in bottle..............................................

More information

Singularity: container formats

Singularity: container formats Singularity Easy to install and configure Easy to run/use: no daemons no root works with scheduling systems User outside container == user inside container Access to host resources Mount (parts of) filesystems

More information

University of Washington Department of Computer Science and Engineering / Department of Statistics

University of Washington Department of Computer Science and Engineering / Department of Statistics University of Washington Department of Computer Science and Engineering / Department of Statistics CSE 547 / Stat 548 Machine Learning (Statistics) for Big Data Homework 2 Winter 2014 Issued: Thursday,

More information

Data needs to be prepped for loading into matlab.

Data needs to be prepped for loading into matlab. Outline Preparing data sets CTD Data from Tomales Bay Clean up Binning Combined Temperature Depth plots T S scatter plots Multiple plots on a single figure What haven't you learned in this class? Preparing

More information

CISE Research Infrastructure: Mid-Scale Infrastructure - NSFCloud (CRI: NSFCloud)

CISE Research Infrastructure: Mid-Scale Infrastructure - NSFCloud (CRI: NSFCloud) Chameleon Cloud Tutorial National Science Foundation Program Solicitation # NSF 13-602 CISE Research Infrastructure: Mid-Scale Infrastructure - NSFCloud (CRI: NSFCloud) Cloud - API Objectives In this tutorial,

More information

Lab 1: Cipher Fundamentals

Lab 1: Cipher Fundamentals Lab 1: Cipher Fundamentals Objective: The key objective of this lab is to be introduced to some of the fundamental principles involved in cryptography, including the usage of Base-64, hexadecimal, the

More information

TPS Documentation. Release Thomas Roten

TPS Documentation. Release Thomas Roten TPS Documentation Release 0.1.0 Thomas Roten Sep 27, 2017 Contents 1 TPS: TargetProcess in Python! 3 2 Installation 5 3 Contributing 7 3.1 Types of Contributions..........................................

More information

Support for Vanilla Universe Checkpointing. Thomas Downes University of Wisconsin-Milwaukee (LIGO)

Support for Vanilla Universe Checkpointing. Thomas Downes University of Wisconsin-Milwaukee (LIGO) Support for Vanilla Universe Checkpointing Thomas Downes University of Wisconsin-Milwaukee (LIGO) Experimental feature! All features discussed are present in the official 8.5 releases. The Morgridge Institute

More information

Embedded M2M Software Testing

Embedded M2M Software Testing Embedded M2M Software Testing Slide 1 Neratec Overview WLAN Products Industrial Wireless LAN Stations WLAN Outdoor Access Points WLAN Module high performance, long distance M2M/IoT and Wireless Sensor

More information

CSE 252A Computer Vision Homework 3 Instructor: Ben Ochoa Due : Monday, November 21, 2016, 11:59 PM

CSE 252A Computer Vision Homework 3 Instructor: Ben Ochoa Due : Monday, November 21, 2016, 11:59 PM CSE 252A Computer Vision Homework 3 Instructor: Ben Ochoa Due : Monday, November 21, 2016, 11:59 PM Instructions: Homework 3 has to be submitted in groups of 3. Review the academic integrity and collaboration

More information

COSC 490 Computational Topology

COSC 490 Computational Topology COSC 490 Computational Topology Dr. Joe Anderson Fall 2018 Salisbury University Course Structure Weeks 1-2: Python and Basic Data Processing Python commonly used in industry & academia Weeks 3-6: Group

More information

sensor-documentation Documentation

sensor-documentation Documentation sensor-documentation Documentation Release 0.0.1 Apoorv Jagtap October 15, 2016 Contents 1 Contents: 1 1.1 Introduction............................................... 1 1.2 Velodyne VLP - 16............................................

More information

CS1110 Lab 5: Practice for A4 (Mar 8-9, 2016) First Name: Last Name: NetID:

CS1110 Lab 5: Practice for A4 (Mar 8-9, 2016) First Name: Last Name: NetID: CS1110 Lab 5: Practice for A4 (Mar 8-9, 2016) First Name: Last Name: NetID: The lab assignments are very important. Remember this: The lab problems feed into the assignments and the assignments define

More information

MultiVariate Bayesian (MVB) decoding of brain images

MultiVariate Bayesian (MVB) decoding of brain images MultiVariate Bayesian (MVB) decoding of brain images Alexa Morcom Edinburgh SPM course 2015 With thanks to J. Daunizeau, K. Brodersen for slides stimulus behaviour encoding of sensorial or cognitive state?

More information

CS252 Graduate Computer Architecture

CS252 Graduate Computer Architecture CS252 Graduate Computer Architecture University of California Dept. of Electrical Engineering and Computer Sciences David E. Culler Spring 2005 Last name: Solutions First name I certify that my answers

More information

Part 1: Installing MongoDB

Part 1: Installing MongoDB Samantha Orogvany-Charpentier CSU ID: 2570586 Installing NoSQL Systems Part 1: Installing MongoDB For my lab, I installed MongoDB version 3.2.12 on Ubuntu 16.04. I followed the instructions detailed at

More information

HANDS ON DATA MINING. By Amit Somech. Workshop in Data-science, March 2016

HANDS ON DATA MINING. By Amit Somech. Workshop in Data-science, March 2016 HANDS ON DATA MINING By Amit Somech Workshop in Data-science, March 2016 AGENDA Before you start TextEditors Some Excel Recap Setting up Python environment PIP ipython Scientific computation in Python

More information

Homework 7: Sudoku. Preliminaries. Overview

Homework 7: Sudoku. Preliminaries. Overview Homework 7: Sudoku For this assignment, you will write a Sudoku solver. To do so, you will (1) use Scala collections extensively, (2) implement a backtracking search algorithm, and (3) implement constraint

More information

Running Blockchain in Docker Containers Prerequisites Sign up for a LinuxONE Community Cloud trial account Deploy a virtual server instance

Running Blockchain in Docker Containers Prerequisites Sign up for a LinuxONE Community Cloud trial account Deploy a virtual server instance Running Blockchain in Docker Containers The following instructions can be used to install the current hyperledger fabric, and run Docker and blockchain code in IBM LinuxONE Community Cloud instances. This

More information

TENSORRT 3.0. DU _v3.0 February Installation Guide

TENSORRT 3.0. DU _v3.0 February Installation Guide TENSORRT 3.0 DU-08731-001_v3.0 February 2018 Installation Guide TABLE OF CONTENTS Chapter 1. Overview... 1 Chapter 2. Getting Started... 2 Chapter 3. Downloading TensorRT...4 Chapter 4. Installing TensorRT...

More information

If you had a freshly generated image from an LCI instructor, make sure to set the hostnames again:

If you had a freshly generated image from an LCI instructor, make sure to set the hostnames again: Storage Node Setup A storage node (or system as your scale) is a very important unit for an HPC cluster. The computation is often about the data it produces and keeping that data safe is important. Safe

More information

WiSE-MNet. Wireless Simulation Environment for Multimedia Networks. User s Manual. Christian Nastasi

WiSE-MNet. Wireless Simulation Environment for Multimedia Networks. User s Manual. Christian Nastasi WiSE-MNet Wireless Simulation Environment for Multimedia Networks User s Manual Christian Nastasi (c.nastasi@sssup.it, nastasichr@gmail.com) December 4, 2011 Contents 1 Introduction 1 2 Overview 2 2.1

More information

Windows cold wallet managing Linux VPS connected Masternode

Windows cold wallet managing Linux VPS connected Masternode Discount Coin Masternodes How to setup a Discount Coin Masternode Single and Multiple masternodes Windows cold wallet managing Linux VPS connected Masternode Version 1.0.2 The DiscountCoin Core Team February

More information

Lecture 6: more pandas (and git/github) LING 1340/2340: Data Science for Linguists Na-Rae Han

Lecture 6: more pandas (and git/github) LING 1340/2340: Data Science for Linguists Na-Rae Han Lecture 6: more pandas (and git/github) LING 1340/2340: Data Science for Linguists Na-Rae Han Objectives git and GitHub: Let's be more disciplined! Python's pandas library Tools: Git and GitHub Jupyter

More information

Episode Engine & Final Cut Server

Episode Engine & Final Cut Server How to Integrate Episode Engine & Final Cut Server Episode Engine can be integrated with Final Cut Server to extend format support and enhance the transcoding speed. This document walks you through the

More information

ViTraM: VIsualization of TRAnscriptional Modules

ViTraM: VIsualization of TRAnscriptional Modules ViTraM: VIsualization of TRAnscriptional Modules Version 2.0 October 1st, 2009 KULeuven, Belgium 1 Contents 1 INTRODUCTION AND INSTALLATION... 4 1.1 Introduction...4 1.2 Software structure...5 1.3 Requirements...5

More information

ENGI-7680 Laboratory Experiments

ENGI-7680 Laboratory Experiments ENGI-7680 Laboratory Experiments Dr. Vlastimil Masek March 22, 2017 1 Experiment 1.1 Exercise - HMI with Voice Output Use a C library for text-to-speech conversion Flite which is documented at http://www.festvox.org/flite.

More information

Mathematics Success Grade 6

Mathematics Success Grade 6 Mathematics Success Grade 6 T683 [OBJECTIVE] The student will determine the volume of rectangular prisms with fractional edge lengths and solve problems in mathematical and real-world situations. [PREREQUISITE

More information

Masternode Setup Guide

Masternode Setup Guide Masternode Setup Guide What this guide is This guide is aimed at anyone who wants to run a Reliance masternode on an Ubuntu 16.04 VPS. What this guide is not A tutorial for linux. What I mean by that,

More information

About the Tutorial. Audience. Prerequisites. Copyright & Disclaimer. Gerrit

About the Tutorial. Audience. Prerequisites. Copyright & Disclaimer. Gerrit Gerrit About the Tutorial Gerrit is a web-based code review tool, which is integrated with Git and built on top of Git version control system (helps developers to work together and maintain the history

More information