NeuroMem. A Neuromorphic Memory patented architecture. NeuroMem 1

Similar documents
CogniSight, image recognition engine

CurieNeurons library

NeuroMem API Open Source Library PATTERN LEARNING AND RECOGNITION WITH A NEUROMEM NETWORK

Unleashing the neurons of the Intel Curie module on the Arduino/Genuino 101 platform

We are changing the way the world computes

Changing the way the world compute. General Vision Inc. (rev 2016)

NeuroShield User s Guide. Version 1.0.5, Feb 2018

CogniPat SDK User s Manual SOFTWARE DEVELOPMENT KIT FOR PATTERN LEARNING AND RECOGNITION WITH NEUROMEM SILICON NETWORK

NM500 User s Manual. NeuroMem chip, 576 neurons Version Revised 01/09/2019

3D Wafer Scale Integration: A Scaling Path to an Intelligent Machine

2. Basic Task of Pattern Classification

Image Knowledge Builder

Computer Vision with MATLAB MATLAB Expo 2012 Steve Kuznicki

BrainCard, Low-power, trainable pattern recognition for IoT

Image Knowledge Builder

Announcements. Recognition. Recognition. Recognition. Recognition. Homework 3 is due May 18, 11:59 PM Reading: Computer Vision I CSE 152 Lecture 14

Computer Vision with MATLAB

NI Smart Cameras PRODUCT FLYER CONTENTS. Have a question? Contact Us.

Segmentation, Classification &Tracking of Humans for Smart Airbag Applications

Building a Next Generation Data Logging System

ECG782: Multidimensional Digital Signal Processing

Elysium Technologies Private Limited::IEEE Final year Project

Jarek Szlichta

Multiple-Choice Questionnaire Group C

POINT-CLOUD PROCESSING USING HDL CODER. April 17th 2018

Opportunities for ML Analytics at the Sensor Endpoint

Design Challenges for Sensor Data Analytics in Internet of Things (IoT)

IN-MEMORY ASSOCIATIVE COMPUTING

Embarquez votre Intelligence Artificielle (IA) sur CPU, GPU et FPGA

Some fast and compact neural network solutions for artificial intelligence applications

Object Recognition. Lecture 11, April 21 st, Lexing Xie. EE4830 Digital Image Processing

Efficient Indexing and Searching Framework for Unstructured Data

Servosila Robotic Heads

Clustering & Classification (chapter 15)

Hardware Neuronale Netzwerke - Lernen durch künstliche Evolution (?)

Brainchip OCTOBER

A Scalable Speech Recognizer with Deep-Neural-Network Acoustic Models

May Wu, Ravi Iyer, Yatin Hoskote, Steven Zhang, Julio Zamora, German Fabila, Ilya Klotchkov, Mukesh Bhartiya. August, 2015

Data Mining. Jeff M. Phillips. January 7, 2019 CS 5140 / CS 6140

AN OVERVIEW OF MICRON S

Computer Systems. Communication (networks, radio links) Meatware (people, users don t forget them)

Internet Data Acquisition

davidklee.net gplus.to/kleegeek linked.com/a/davidaklee

Data Mining. Jeff M. Phillips. January 8, 2014

Exploiting the OpenPOWER Platform for Big Data Analytics and Cognitive. Rajesh Bordawekar and Ruchir Puri IBM T. J. Watson Research Center

Parallelizing Graphics Pipeline Execution (+ Basics of Characterizing a Rendering Workload)

NI Vision Platform. Radim ŠTEFAN. ni.com

JAVA Projects. 1. Enforcing Multitenancy for Cloud Computing Environments (IEEE 2012).

Privacy Preserving Ranked Multi-Keyword Search for Multiple Data Owners in Cloud Computing

Distributed Vision Processing in Smart Camera Networks

Outrun Your Competition With SAS In-Memory Analytics Sascha Schubert Global Technology Practice, SAS

Recognize Virtually Any Shape by Oliver Sidla

IEEE 2013 JAVA PROJECTS Contact No: KNOWLEDGE AND DATA ENGINEERING

FYS Data acquisition & control. Introduction. Spring 2018 Lecture #1. Reading: RWI (Real World Instrumentation) Chapter 1.

Enable AI on Mobile Devices

Course Outcome of M.E (ECE)

TIOVX TI s OpenVX Implementation

An Oracle White Paper October Oracle Social Cloud Platform Text Analytics

Data Mining. Jeff M. Phillips. January 12, 2015 CS 5140 / CS 6140

CHAPTER 4 DETECTION OF DISEASES IN PLANT LEAF USING IMAGE SEGMENTATION

6.1 Multiprocessor Computing Environment

Bus Detection and recognition for visually impaired people

Parallelizing Graphics Pipeline Execution (+ Basics of Characterizing a Rendering Workload)

CMOS USORIA. Features

INTRODUCTION TO BIG DATA, DATA MINING, AND MACHINE LEARNING

Lecture 1: Gentle Introduction to GPUs

Name of the lecturer Doç. Dr. Selma Ayşe ÖZEL

Advanced Parallel Programming I

Content Based Image Retrieval (CBIR) Using Segmentation Process

COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor

This tutorial has been prepared for computer science graduates to help them understand the basic-to-advanced concepts related to data mining.

T chnology chnology Ma turity turity for fo Adaptiv Adaptiv Massively Massiv ely Pa P ra r llel llel Computing F rst rst Wo W rksho p 2009

Machine Learning in the Process Industry. Anders Hedlund Analytics Specialist

EE795: Computer Vision and Intelligent Systems

Machine Learning in Biology

Pouya Kousha Fall 2018 CSE 5194 Prof. DK Panda

A SURVEY OF IMAGE MINING TECHNIQUES AND APPLICATIONS

Simplifying FPGA Design for SDR with a Network on Chip Architecture

Managing data flows. Martyn Winn Scientific Computing Dept. STFC Daresbury Laboratory Cheshire. 8th May 2014

Data Mining. Jeff M. Phillips. January 9, 2013

Robotics Programming Laboratory

AUTOMATIC VIDEO INDEXING

SpiNNaker a Neuromorphic Supercomputer. Steve Temple University of Manchester, UK SOS21-21 Mar 2017

C. The system is equally reliable for classifying any one of the eight logo types 78% of the time.

GPU-Accelerated Incremental Correlation Clustering of Large Data with Visual Feedback

Nowcasting. D B M G Data Base and Data Mining Group of Politecnico di Torino. Big Data: Hype or Hallelujah? Big data hype?

CSCI 4717 Computer Architecture

Dietrich Paulus Joachim Hornegger. Pattern Recognition of Images and Speech in C++

Neural Computer Architectures

Search Engines. Information Retrieval in Practice

Intel s s Memory Strategy for the Wireless Phone

Templates, Image Pyramids, and Filter Banks

Embedded Computing Platform. Architecture and Instruction Set

Goldeye CL-032. Description. Goldeye CL all purpose SWIR camera

Catapult: A Reconfigurable Fabric for Petaflop Computing in the Cloud

Colour Object Counting and Sorting Mechanism Using Image Processing Approach Avadhoot R.Telepatil 1, 2 Prashant M. Jadhav 2 1

Announcements. Recognition I. Gradient Space (p,q) What is the reflectance map?

Machine Learning : Clustering, Self-Organizing Maps

The Xilinx XC6200 chip, the software tools and the board development tools

How to Build Optimized ML Applications with Arm Software

Transcription:

NeuroMem A Neuromorphic Memory patented architecture NeuroMem 1

Unique simple architecture NM bus A chain of identical neurons, no supervisor 1 neuron = memory + logic gates Context Category ted during Memory the interconnection time Distance Active IF Identifier Read only NeuroMem 2

NeuroMem key features Learn by examples Adaptive, Incremental, Contextual Real-time or Off-line Supervised or unsupervised Recognize by association Radial Basis Function (RBF) Fastest K Nearest Neighbor (KNN) Winner Takes All Knowledge building On the Go, expandable Traceability and portability Imaging driving without the yellow light STO P GO IT DEPENDS! NeuroMem 3

NeuroMem Value Proposition Content addressability Data is recognized in-place within memory avoiding the memory access bottleneck Exact or fuzzy content matching Matches are inherently sorted by the hardware No need to sort data for indexing Massive scalability Neuron density scales with Moore s law Intra-chip and inter-chip connectivity through same bus Fixed pin count regardless of neuron density/chip Same IOs regardless of chip density/design (c) NeuroMem 4

Fixed µsec latency per recognition What s in this object? Pentium/DSP CPU NeuroMem Sequential search Increasing time High consumption (Ghz) Heavy software Complex scalability no no no Step 1 Step 2 Step 3 Step 1 neuron 1 neuron 2 neuron 3 Parallel search Constant search (ns) Low power (Mhz) No software Simple expansion neuron 4 yes Step x neuron x yes! neuron z NeuroMem 5

NeuroMem seen as a 3-layer NN Input layer (up to 256 bytes) Hidden layer Single neuron: - 256 bytes RAM - 3000 logic gates Output layer (2 bytes) WTA bus Neuron Select 1 Feedback Σ F(x) 256 synapses CM1K= 1024 neurons x 256 synapses per neuron = 262,144 synaptic connections of 8-bits DCI Inhibitor Category DCO WTA (c) NeuroMem 6

Ready to support multiple NN, segmented into context NeuroMem 7

NeuroMem ecosystem Application deployment NeuroMem 8

Simple interface to the neurons Text (1D) Signal (1D) Broadcast Pattern/ Stimuli Teach = Write category Image (2D) Knowledge Video (3D) Recognize = Read category Action NeuroMem 9

A fine balance Your Job: Select representative examples Define discriminant features Annotate for teaching Query for recognition results Define final decision rules NeuroMem Job: Learn the feature vectors Build the decision space (aka knowledge) Recognize feature vectors per decreasing level of confidence Save and restore a knowledge For portability For backup NeuroMem 10

What is a feature vector? Examples for text data Vectors = ASCII codes of parsed words Examples for signal data Sample at a given frequency rate Spectrum, FFTs, Mel Ceptrum Coefficients Examples for image data Pixel subsampling Histograms of intensities, gradients SURFS, SIFTS, Doughman vector Must be formatted to fit into 256 bytes for the neurons NeuroMem 11

Extracting feature vectors Knowledge Builder Tools Programming IDE MatLab, LabVIEW C/C++, C#, Python Arduino NeuroMem 12

NeuroMem Use Models Images FE=Feature Vectors Identification Videos FE Classification Voice FE NeuroMem Categories Anomaly detection Novelty detection Signal Distances Clustering Text FE N identifiers Tracking Template matching Data NeuroMem 13

How many neurons do I need? Depends on the application, the variability of the data, etc. A few examples in image recognition Application Description Estimated Neurons /Object Fish sorting Classification of herrings (Accept, Reject, Recycle) passing on an in-line conveyor belt Glass Inspection Detection of anomalies of texture in patterned solar glass passing on a conveyor Inkjet OCR Reading of date code or serial numbers printed 1-3 /digit on a packaging Cooperative face Identifying a person facing front, positioned at a 5/person recognition known distance of the camera, willing to remove her glasses if needed to be recognized Semantic analysis Counting the occurrences of words from a 1/word dictionary in live tweets, posts and other text streams. Total neurons 200 800 NeuroMem 14

Cascade classifiers Source image Transform image Heron beak Stork beak Heron eye Heron neck Aigrette neck Recognized objects Heron Semantic Recognition Engine #1 Engine for primitive block conditioning - Adaptive gain control - Noise removal, - Edge extraction - Compression, more Recognition Engine #2 Engine for object recognition - Object identification - Anomaly detection - Target location, more Recognition Engine #3 Engine for decision making - Data mining - Clustering - Contextual localization (c) General Vision Inc.

Application deployment workflow Acquisition Domain expert Training platforms / Execution Platform Stimuli Decision Raw data Annotate Annotations Acquisition Decision Application Analyst Knowledge Builder Apps and Tools Libraries of feature extractions Knowledge Embedded Programming Configuration Programmer NeuroMem 16

NeuroMem Based System Architecture Cognitive Sensing Cognitive networking Cognitive storage NeuroMem 17

Cognitive Sensing Systems Input/Sensors CMOS Audio sensor Biosensor Search Engine next to sensor Detect, Identify, Classify, Track Output Actuator Transmission Storage Sensor Hub: CMOS, n-axis MEMS, AUDIO MEMS, BioSensors Applications Industrial inspection Building and home automation Automotive Configurable Search Engine (FPGA + ARM Core) Working buffer n Mbytes Consumer electronics Wearables and health I/O lines NeuroMem 18

Cognitive Networking Systems Data type Text Signal and audio files Image and movie files Input Incoming data stream Stored data Output Filtered output data stream Stored source data With Meta data Selective storage With Meta data Input stream Configurable Search Engine (FPGA + ARM Core) Working buffer n Mbytes Applications Denial of service Secure uplink/downlink Twitter analytics Video filtering Output stream NeuroMem 19

Cognitive Storage Systems Input Stored data Input data stream Text, audio files Image and movie files Output Meta data Non-volatile Storage n Gbytes: Text files, Audio files, Image files, Movie files Configurable Search Engine (FPGA + ARM Core) SSD High-Speed bus Filtered data Working buffer n Mbytes Applications Text analytics, Bioinformatics Image and videos analytics Big data NeuroMem 20

Summary Learn from examples Recognize by association RBF classifier Knows when it does not know Accept uncertainties NeuroMem Complementary KNN Fixed latency to learn Fixed latency to recognize Parallel architecture Partitioned dynamically per context Low power Expandable (c) NeuroMem 21