Header

UZH-Logo

Maintenance Infos

TrueHappiness: Neuromorphic Emotion Recognition on TrueNorth


Diehl, Peter U; Pedroni, Bruno U; Cassidy, Andrew; Merolla, Paul; Neftci, Emre; Zarrella, Guido (2016). TrueHappiness: Neuromorphic Emotion Recognition on TrueNorth. In: 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada, 25 July 2016 - 29 July 2016.

Abstract

We present an approach to constructing a neuromorphic device that responds to language input by producing neuron spikes in proportion to the strength of the appropriate positive or negative emotional response. Specifically, we perform a fine-grained sentiment analysis task with implementations on two different systems: one using conventional spiking neural network (SNN) simulators and the other one using IBM's Neurosynaptic System TrueNorth. Input words are projected into a high-dimensional semantic space and processed through a fully-connected neural network (FCNN) containing rectified linear units (ReLU) trained via backpropagation. After training, this FCNN is converted to a SNN by substituting the ReLUs with integrate-and-fire neurons. We show that there is practically no performance loss due to conversion to a spiking network on a sentiment analysis test set, i.e. correlations with human annotations differ by less than 0.02 between the original DNN and its spiking equivalent. Additionally, we show that the SNN generated with this technique can be mapped to existing neuromorphic hardware - in our case, the TrueNorth chip. Mapping to the chip involves 4-bit synaptic weight discretization and adjustment of the neuron thresholds. The resulting end-to-end system can take a user input, i.e. a word in a vocabulary of over 300,000 words, and estimate its sentiment on TrueNorth with a power consumption of approximately 50 μW.

Abstract

We present an approach to constructing a neuromorphic device that responds to language input by producing neuron spikes in proportion to the strength of the appropriate positive or negative emotional response. Specifically, we perform a fine-grained sentiment analysis task with implementations on two different systems: one using conventional spiking neural network (SNN) simulators and the other one using IBM's Neurosynaptic System TrueNorth. Input words are projected into a high-dimensional semantic space and processed through a fully-connected neural network (FCNN) containing rectified linear units (ReLU) trained via backpropagation. After training, this FCNN is converted to a SNN by substituting the ReLUs with integrate-and-fire neurons. We show that there is practically no performance loss due to conversion to a spiking network on a sentiment analysis test set, i.e. correlations with human annotations differ by less than 0.02 between the original DNN and its spiking equivalent. Additionally, we show that the SNN generated with this technique can be mapped to existing neuromorphic hardware - in our case, the TrueNorth chip. Mapping to the chip involves 4-bit synaptic weight discretization and adjustment of the neuron thresholds. The resulting end-to-end system can take a user input, i.e. a word in a vocabulary of over 300,000 words, and estimate its sentiment on TrueNorth with a power consumption of approximately 50 μW.

Statistics

Altmetrics

Downloads

1 download since deposited on 27 Jan 2017
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Speech), original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:29 July 2016
Deposited On:27 Jan 2017 12:10
Last Modified:31 Mar 2017 07:09
Publisher:Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN)
Series Name:IEEE International Joint Conference on Neural Networks
Publisher DOI:https://doi.org/10.1109/IJCNN.2016.7727758
Official URL:http://ieeexplore.ieee.org/document/7727758/

Download

Preview Icon on Download
Filetype: PDF - Registered users only
Size: 370kB
View at publisher

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations