Personal tools

Difference between revisions of "Hyperdimensional Computing"

From iis-projects

Jump to: navigation, search
Line 1: Line 1:
 
[[File:Brain-circuit.png|thumb]]
 
[[File:Brain-circuit.png|thumb]]
==Introduction==
+
=Introduction=
 
The way the brain works suggests that rather than working with numbers that we are used to, computing with high-dimensional (HD) vectors, e.g., 10,000 bits is more efficient.
 
The way the brain works suggests that rather than working with numbers that we are used to, computing with high-dimensional (HD) vectors, e.g., 10,000 bits is more efficient.
 
Computing with HD vectors, referred to as “hypervectors,” offers a general and scalable model of computing as well as well-defined set of arithmetic operations that can enable fast and one-shot learning (no need of back-propagation like in neural networks). Furthermore it is memory-centric with embarrassingly parallel operations and is extremely robust against most failure mechanisms and noise.  
 
Computing with HD vectors, referred to as “hypervectors,” offers a general and scalable model of computing as well as well-defined set of arithmetic operations that can enable fast and one-shot learning (no need of back-propagation like in neural networks). Furthermore it is memory-centric with embarrassingly parallel operations and is extremely robust against most failure mechanisms and noise.  
 
Such generality, robustness against data uncertainty, and one-shot learning make HD computing a prime candidate for utilization in application domains such as: brain-computer interfaces, biosignal processing (e.g., EEG/ECoG/EMG), robotics, voice/video classification, language recognition, text categorization, scene reasoning, analogical-based reasoning, etc.
 
Such generality, robustness against data uncertainty, and one-shot learning make HD computing a prime candidate for utilization in application domains such as: brain-computer interfaces, biosignal processing (e.g., EEG/ECoG/EMG), robotics, voice/video classification, language recognition, text categorization, scene reasoning, analogical-based reasoning, etc.
  
Hypervectors are high-dimensional (e.g., 10,000 dimensions), they are (pseudo)random with independent identically distributed components and holographically distributed (i.e., not microcoded). Hypervectors can use various coding: dense or sparse, bipolar or binary and can be combined using arithmetic operations such as multiplication, addition, and permutation. The vectors can be compared for similarity using distance metrics
+
Hypervectors are high-dimensional (e.g., 10,000 dimensions), they are (pseudo)random with independent identically distributed components and holographically distributed (i.e., not microcoded). Hypervectors can use various coding: dense or sparse, bipolar or binary and can be combined using arithmetic operations such as multiplication, addition, and permutation. The vectors can be compared for similarity using distance metrics.
 +
 
 +
Here, we provide a list of related projects fro your information. If you are interested to work in this area please contact us for more details.
 +
 
 +
 
 +
=Available Projects=
 +
==Epilepsy Seizure Prediction==
 +
[[File:Seizure-prediction.png|thumb]]
 +
===Short Description===
 +
Seizure prediction systems hold promise for improving the quality of life for patients with epilepsy that afflicts nearly 1% of the world's population.
 +
In this project, your goal would be to develop efficient algorithms for EEG as well as non-EEG signals to predict an upcoming seizure in a low power device.
 +
The abilities of HD computing for one-shot and online learning come to rescue.
 +
===Links===
 +
* [https://www.kaggle.com/c/seizure-prediction American Epilepsy Society Seizure Prediction Challenge]
 +
 
 +
==Online Brain--Computer Interfaces==
 +
[[File:Seizure-prediction.png|thumb]]
 +
===Short Description===
 +
Seizure prediction systems hold promise for improving the quality of life for patients with epilepsy that afflicts nearly 1% of the world's population.
 +
In this project, your goal would be to develop efficient algorithms for EEG as well as non-EEG signals to predict an upcoming seizure in a low power device.
 +
The abilities of HD computing for one-shot and online learning come to rescue.
 +
===Links===
 +
* [https://www.kaggle.com/c/seizure-prediction American Epilepsy Society Seizure Prediction Challenge]
 +
 +
 
 +
https://bwrc.eecs.berkeley.edu/sites/default/files/files/u2630/flexemg_v2_lq.mp4#t=2
 +
 
  
 
In this project, your goal would be to develop an RTL implementation of HD computing for an EMG-based hand gesture recognition system with fast learning using much lower power than ever before.   
 
In this project, your goal would be to develop an RTL implementation of HD computing for an EMG-based hand gesture recognition system with fast learning using much lower power than ever before.   

Revision as of 12:44, 7 November 2017

Brain-circuit.png

Introduction

The way the brain works suggests that rather than working with numbers that we are used to, computing with high-dimensional (HD) vectors, e.g., 10,000 bits is more efficient. Computing with HD vectors, referred to as “hypervectors,” offers a general and scalable model of computing as well as well-defined set of arithmetic operations that can enable fast and one-shot learning (no need of back-propagation like in neural networks). Furthermore it is memory-centric with embarrassingly parallel operations and is extremely robust against most failure mechanisms and noise. Such generality, robustness against data uncertainty, and one-shot learning make HD computing a prime candidate for utilization in application domains such as: brain-computer interfaces, biosignal processing (e.g., EEG/ECoG/EMG), robotics, voice/video classification, language recognition, text categorization, scene reasoning, analogical-based reasoning, etc.

Hypervectors are high-dimensional (e.g., 10,000 dimensions), they are (pseudo)random with independent identically distributed components and holographically distributed (i.e., not microcoded). Hypervectors can use various coding: dense or sparse, bipolar or binary and can be combined using arithmetic operations such as multiplication, addition, and permutation. The vectors can be compared for similarity using distance metrics.

Here, we provide a list of related projects fro your information. If you are interested to work in this area please contact us for more details.


Available Projects

Epilepsy Seizure Prediction

Seizure-prediction.png

Short Description

Seizure prediction systems hold promise for improving the quality of life for patients with epilepsy that afflicts nearly 1% of the world's population. In this project, your goal would be to develop efficient algorithms for EEG as well as non-EEG signals to predict an upcoming seizure in a low power device. The abilities of HD computing for one-shot and online learning come to rescue.

Links

Online Brain--Computer Interfaces

Seizure-prediction.png

Short Description

Seizure prediction systems hold promise for improving the quality of life for patients with epilepsy that afflicts nearly 1% of the world's population. In this project, your goal would be to develop efficient algorithms for EEG as well as non-EEG signals to predict an upcoming seizure in a low power device. The abilities of HD computing for one-shot and online learning come to rescue.

Links


https://bwrc.eecs.berkeley.edu/sites/default/files/files/u2630/flexemg_v2_lq.mp4#t=2


In this project, your goal would be to develop an RTL implementation of HD computing for an EMG-based hand gesture recognition system with fast learning using much lower power than ever before.


Who are we What do we do Where to find us


Available Projects


Projects In Progress


Completed Projects