Luiz Pessoa

Marwen Belkaid, Luiz Pessoa

Over the past decades, research in cognitive and affective neuroscience has emphasized that emotion is crucial for human intelligence and in fact inseparable from cognition. Concurrently, there has been growing interest in simulating and modeling emotion-related processes in robots and artificial agents. In this opinion paper, our goal is to provide a snapshot of the present landscape in emotion modeling and to show how neuroscience can help advance the current state of the art. We start with an overview of the existing literature on emotion modeling in three areas of research: affective computing, social robotics, and neurorobotics. Briefly summarizing the current state of knowledge on natural emotion, we then highlight how existing proposals in artificial emotion do not make sufficient contact with neuroscientific evidence. We conclude by providing a set of principles to help guide future research in artificial emotion and intelligent machines more generally. Overall, we argue that a stronger integration of emotion-related processes in robot models is critical for the design of human-like behavior in future intelligent machines. Such integration not only will contribute to the development of autonomous social machines capable of tackling real-world problems but would contribute to advancing understanding of human emotion.

Aya Abdelsalam Ismail, Mohamed Gunady, Luiz Pessoa et al.

Recent efforts to improve the interpretability of deep neural networks use saliency to characterize the importance of input features to predictions made by models. Work on interpretability using saliency-based methods on Recurrent Neural Networks (RNNs) has mostly targeted language tasks, and their applicability to time series data is less understood. In this work we analyze saliency-based methods for RNNs, both classical and gated cell architectures. We show that RNN saliency vanishes over time, biasing detection of salient features only to later time steps and are, therefore, incapable of reliably detecting important features at arbitrary time intervals. To address this vanishing saliency problem, we propose a novel RNN cell structure (input-cell attention), which can extend any RNN cell architecture. At each time step, instead of only looking at the current input vector, input-cell attention uses a fixed-size matrix embedding, each row of the matrix attending to different inputs from current or previous time steps. Using synthetic data, we show that the saliency map produced by the input-cell attention RNN is able to faithfully detect important features regardless of their occurrence in time. We also apply the input-cell attention RNN on a neuroscience task analyzing functional Magnetic Resonance Imaging (fMRI) data for human subjects performing a variety of tasks. In this case, we use saliency to characterize brain regions (input features) for which activity is important to distinguish between tasks. We show that standard RNN architectures are only capable of detecting important brain regions in the last few time steps of the fMRI data, while the input-cell attention model is able to detect important brain region activity across time without latter time step biases.