TrueHappiness: Neuromorphic Emotion Recognition on TrueNorth
Peter U. Diehl, Bruno U. Pedroni, Andrew Cassidy, Paul Merolla, Emre, Neftci, Guido Zarrella

TL;DR
This paper demonstrates a neuromorphic sentiment analysis system that converts a trained neural network into a spiking neural network, maintains accuracy, and runs efficiently on TrueNorth hardware for emotion recognition from language.
Contribution
It introduces a method to convert deep neural networks into spiking neural networks with minimal performance loss and implements this on TrueNorth for low-power sentiment analysis.
Findings
Minimal performance loss after conversion to SNN
Successful mapping of SNN to TrueNorth hardware
Power-efficient sentiment analysis at 50 uW
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 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 between…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
