CBGT-Net: A Neuromimetic Architecture for Robust Classification of Streaming Data

TL;DR

The proposed CBGT-Net provides improved accuracy and robustness compared to models trained to classify from a single patch, and models leveraging an LSTM layer to classify from a fixed sequence length of patches.

Abstract

This paper describes CBGT-Net, a neural network model inspired by the cortico-basal ganglia-thalamic (CBGT) circuits found in mammalian brains. Unlike traditional neural network models, which either generate an output for each provided input, or an output after a fixed sequence of inputs, the CBGT-Net learns to produce an output after a sufficient criteria for evidence is achieved from a stream of observed data. For each observation, the CBGT-Net generates a vector that explicitly represents the amount of evidence the observation provides for each potential decision, accumulates the evidence over time, and generates a decision when the accumulated evidence exceeds a pre-defined threshold. We evaluate the proposed model on two image classification tasks, where models need to predict image categories based on a stream of small patches extracted from the image. We show that the CBGT-Net provides improved accuracy and robustness compared to models trained to classify from a single patch, and models leveraging an LSTM layer to classify from a fixed sequence length of patches.

Figures (6)

• Figure 1: Main components of the CBGT-Net architecture.
• Figure 2: Example episode from CIFAR-10 environment: a sequence of three patches from an image in the "dog" category.
• Figure 3: Inference accuracy of the CBGT-Net and baselines as a function of decision time for the MNIST Environment. Markers on the CBGT-Net results indicate the average decision time for models with a given threshold value. LSTM models were trained with sequence lengths corresponding to the nearest value above corresponding CBGT-Net decision times.
• Figure 4: Inference accuracy of the CBGT-Net and baselines as a function of decision time for the CIFAR-10 Environment. Markers on the CBGT-Net results indicate the average decision time for models with a given threshold value. LSTM models were trained with sequence lengths corresponding to the nearest value above corresponding CBGT-Net decision times.
• Figure 5: Average Decision Time taken by CBGT_Net trained at different threshold values ($\tau$) on MNIST (Fig. a) and CIFAR10 (Fig. b) Environments for different patch size observations