Portrait of Pouya Bashivan is unavailable

Pouya Bashivan

Associate Academic Member
Assistant Professor, McGill University, Department of Physiology


Pouya Bashivan is an assistant professor in the Department of Physiology at McGill University, a member of McGill’s Integrated Program in Neuroscience, and an associate academic member of Mila – Quebec Artificial Intelligence Institute.

Before joining McGill University, Bashivan was a postdoctoral fellow at Mila, where he worked with Irina Rish and Blake Richards. Prior to that, he was a postdoctoral researcher in the Department of Brain and Cognitive Sciences and at the McGovern Institute for Brain Research at MIT, where he worked with James DiCarlo.

He received his PhD in computer engineering from the University of Memphis in 2016, and his BSc and MSc degrees in electrical and control engineering from K.N. Toosi University of Technology (Tehran).

The goal of research in Bashivan’s lab is to develop neural network models that leverage memory to solve complex tasks. While we often rely on task-performance measures to find improved neural network models and learning algorithms, we also use neural and behavioral measurements from humans and other animal brains to evaluate the similarity of these models to biologically evolved brains. We believe that these additional constraints could expedite the progress towards engineering a human-level artificially intelligent agent.

Current Students

PhD - McGill University
Co-supervisor :
Master's Research - McGill University
Master's Research - McGill University
Master's Research - Université de Montréal
Principal supervisor :
PhD - McGill University


The feature landscape of visual cortex
Rudi Tong
Ronan da Silva
Dongyan Lin
Arna Ghosh
James Wilsenach
Erica Cianfarano
Stuart Trenholm
Understanding computations in the visual system requires a characterization of the distinct feature preferences of neurons in different visu… (see more)al cortical areas. However, we know little about how feature preferences of neurons within a given area relate to that area’s role within the global organization of visual cortex. To address this, we recorded from thousands of neurons across six visual cortical areas in mouse and leveraged generative AI methods combined with closed-loop neuronal recordings to identify each neuron’s visual feature preference. First, we discovered that the mouse’s visual system is globally organized to encode features in a manner invariant to the types of image transformations induced by self-motion. Second, we found differences in the visual feature preferences of each area and that these differences generalized across animals. Finally, we observed that a given area’s collection of preferred stimuli (‘own-stimuli’) drive neurons from the same area more effectively through their dynamic range compared to preferred stimuli from other areas (‘other-stimuli’). As a result, feature preferences of neurons within an area are organized to maximally encode differences among own-stimuli while remaining insensitive to differences among other-stimuli. These results reveal how visual areas work together to efficiently encode information about the external world.
Using modular connectome-based predictive modeling to reveal brain-behavior relationships of individual differences in working memory
Huayi Yang
Junjun Zhang
Zhenlan Jin
Ling Li
Towards Out-of-Distribution Adversarial Robustness
Adam Ibrahim
Charles Guille-Escuret
Adversarial robustness continues to be a major challenge for deep learning. A core issue is that robustness to one type of attack often fail… (see more)s to transfer to other attacks. While prior work establishes a theoretical trade-off in robustness against different
How well do models of visual cortex generalize to out of distribution samples?
Yifei Ren
Learning Robust Kernel Ensembles with Kernel Average Pooling
Adam Ibrahim
Amirozhan Dehghani
Yifei Ren
Adversarial Feature Desensitization
Reza Bayat
Adam Ibrahim
Kartik Ahuja
Mojtaba Faramarzi
Touraj Laleh
Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can … (see more)drastically impair the network's performance. Many defense methods have been proposed for improving robustness of deep networks by training them on adversarially perturbed inputs. However, these models often remain vulnerable to new types of attacks not seen during training, and even to slightly stronger versions of previously seen attacks. In this work, we propose a novel approach to adversarial robustness, which builds upon the insights from the domain adaptation field. Our method, called Adversarial Feature Desensitization (AFD), aims at learning features that are invariant towards adversarial perturbations of the inputs. This is achieved through a game where we learn features that are both predictive and robust (insensitive to adversarial attacks), i.e. cannot be used to discriminate between natural and adversarial data. Empirical results on several benchmarks demonstrate the effectiveness of the proposed approach against a wide range of attack types and attack strengths. Our code is available at https://github.com/BashivanLab/afd.
Continual Learning with Self-Organizing Maps
Martin Schrimpf
Robert Ajemian
Matthew D Riemer
Yuhai Tu
Despite remarkable successes achieved by modern neural networks in a wide range of applications, these networks perform best in domain-speci… (see more)fic stationary environments where they are trained only once on large-scale controlled data repositories. When exposed to non-stationary learning environments, current neural networks tend to forget what they had previously learned, a phenomena known as catastrophic forgetting. Most previous approaches to this problem rely on memory replay buffers which store samples from previously learned tasks, and use them to regularize the learning on new ones. This approach suffers from the important disadvantage of not scaling well to real-life problems in which the memory requirements become enormous. We propose a memoryless method that combines standard supervised neural networks with self-organizing maps to solve the continual learning problem. The role of the self-organizing map is to adaptively cluster the inputs into appropriate task contexts - without explicit labels - and allocate network resources accordingly. Thus, it selectively routes the inputs in accord with previous experience, ensuring that past learning is maintained and does not interfere with current learning. Out method is intuitive, memoryless, and performs on par with current state-of-the-art approaches on standard benchmarks.