Automated Architecture Search for Brain-inspired Hyperdimensional Computing

02/11/2022
by   Junhuan Yang, et al.
10

This paper represents the first effort to explore an automated architecture search for hyperdimensional computing (HDC), a type of brain-inspired neural network. Currently, HDC design is largely carried out in an application-specific ad-hoc manner, which significantly limits its application. Furthermore, the approach leads to inferior accuracy and efficiency, which suggests that HDC cannot perform competitively against deep neural networks. Herein, we present a thorough study to formulate an HDC architecture search space. On top of the search space, we apply reinforcement-learning to automatically explore the HDC architectures. The searched HDC architectures show competitive performance on case studies involving a drug discovery dataset and a language recognition task. On the Clintox dataset, which tries to learn features from developed drugs that passed/failed clinical trials for toxicity reasons, the searched HDC architecture obtains the state-of-the-art ROC-AUC scores, which are 0.80 than conventional neural networks. Similar results are achieved on the language recognition task, with 1.27

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

research
03/23/2021

Neural Architecture Search From Fréchet Task Distance

We formulate a Fréchet-type asymmetric distance between tasks based on F...
research
10/15/2019

State of Compact Architecture Search For Deep Neural Networks

The design of compact deep neural networks is a crucial task to enable w...
research
01/16/2018

GitGraph - Architecture Search Space Creation through Frequent Computational Subgraph Mining

The dramatic success of deep neural networks across multiple application...
research
12/13/2018

IRLAS: Inverse Reinforcement Learning for Architecture Search

In this paper, we propose an inverse reinforcement learning method for a...
research
09/01/2020

Neural Architecture Search For Keyword Spotting

Deep neural networks have recently become a popular solution to keyword ...
research
11/17/2021

Search and Rescue in a Maze-like Environment with Ant and Dijkstra Algorithms

With the growing reliability of modern Ad Hoc Networks, it is encouragin...
research
12/20/2017

A Flexible Approach to Automated RNN Architecture Generation

The process of designing neural architectures requires expert knowledge ...

Please sign up or login with your details

Forgot password? Click here to reset