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.

翻译：本文描述了CBGT-Net，一种受哺乳动物大脑中皮层-基底节-丘脑（CBGT）回路启发的神经网络模型。与传统神经网络模型（要么对每个输入生成一个输出，要么在固定输入序列后生成一个输出）不同，CBGT-Net学习在从流式观测数据中累积到充分证据标准后产生输出。对于每次观测，CBGT-Net生成一个向量，明确表示该观测为每个潜在决策提供的证据量，随时间累积证据，并在累积证据超过预设阈值时生成决策。我们在两个图像分类任务上评估了所提模型，其中模型需要基于从图像中提取的小块流预测图像类别。结果表明，与基于单个图像块分类训练的模型以及利用LSTM层从固定序列长度图像块分类的模型相比，CBGT-Net在准确性和鲁棒性方面均有所提升。