A neural network walks into a lab: towards using deep nets as models for human behavior

Abstract

What might sound like the beginning of a joke has become an attractive prospect for many cognitive scientists: the use of deep neural network models (DNNs) as models of human behavior in perceptual and cognitive tasks. Although DNNs have taken over machine learning, attempts to use them as models of human behavior are still in the early stages. Can they become a versatile model class in the cognitive scientist's toolbox? We first argue why DNNs have the potential to be interesting models of human behavior. We then discuss how that potential can be more fully realized. On the one hand, we argue that the cycle of training, testing, and revising DNNs needs to be revisited through the lens of the cognitive scientist's goals. Specifically, we argue that methods for assessing the goodness of fit between DNN models and human behavior have to date been impoverished. On the other hand, cognitive science might have to start using more complex tasks (including richer stimulus spaces), but doing so might be beneficial for DNN-independent reasons as well. Finally, we highlight avenues where traditional cognitive process models and DNNs may show productive synergy.

References in corpus (25)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Overcoming catastrophic forgetting in neural networks
• Neural Architecture Search with Reinforcement Learning
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• An Overview of Multi-Task Learning in Deep Neural Networks
• Understanding deep learning requires rethinking generalization
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Effective Approaches to Attention-based Neural Machine Translation
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• Adversarial Examples Are Not Bugs, They Are Features
• Learning to reinforcement learn
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• A mathematical theory of semantic development in deep neural networks
• Measuring the tendency of CNNs to Learn Surface Statistical Regularities
• Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
• Comparing deep neural networks against humans: object recognition when the signal gets weaker
• Controversial stimuli: pitting neural networks against each other as models of human recognition
• Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
• Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
• Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
• Adapting Deep Network Features to Capture Psychological Representations
• Learning Inductive Biases with Simple Neural Networks
• Relational recurrent neural networks
• Modeling Human Categorization of Natural Images Using Deep Feature Representations
• The 30-Year Cycle In The AI Debate

Cited by in corpus (6)

• Successes and critical failures of neural networks in capturing human-like speech recognition
• Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention
• Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
• How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
• The Next Big Thing(s) in Unsupervised Machine Learning: Five Lessons from Infant Learning
• Learning Translation Invariance in CNNs