Christopher Manning - 'Building Neural Network Models That Can Reason' (TCSDLS 2017-2018)

Speaker: Christopher Manning, Thomas M. Siebel Professor in Machine Learning and Professor of Linguistics and of Computer Science, Stanford University

Title: Building Neural Network Models That Can Reason

Abstract: Deep learning has had enormous success on perceptual tasks but still struggles in providing a model for inference. To address this gap, we have been developing Memory-Attention-Composition networks (MACnets). The MACnet design provides a strong prior for explicitly iterative reasoning, enabling it to support explainable, structured learning, as well as good generalization from a modest amount of data. The model builds on the great success of existing recurrent cells such as LSTMs: A MacNet is a sequence of a single recurrent Memory, Attention, and Composition (MAC) cell. Its careful design imposes structural constraints on the operation of each cell and the interactions between them, incorporating explicit control and soft attention mechanisms into their interfaces. We demonstrate the model’s strength and robustness on the challenging CLEVR dataset for visual reasoning (Johnson et al. 2016), achieving a new state-of-the-art 98.9% accuracy, halving the error rate of the previous best model. More importantly, we show that the new model is more computationally efficient and data-efficient, requiring an order of magnitude less time and/or data to achieve good results. Joint work with Drew Hudson.