Portrait de Shahab Bakhtiari

Shahab Bakhtiari

Membre académique associé
Professeur adjoint, Université de Montréal, Département de psychologie
Sujets de recherche
Apprentissage de représentations
Apprentissage profond
Neurosciences computationnelles
Vision par ordinateur
Site web
LinkedIn
X

Biographie

Shahab Bakhtiari est professeur adjoint au Département de psychologie de l'Université de Montréal et membre académique associé de Mila – Institut québécois d'intelligence artificielle. Il a obtenu un diplôme de premier cycle et un diplôme d'études supérieures en génie électrique à l'Université de Téhéran. Il a ensuite réalisé un doctorat en neurosciences à l'Université McGill, puis a été chercheur postdoctoral à Mila, où il s'est concentré sur la recherche à l'intersection des neurosciences et de l'intelligence artificielle. Dans ses travaux, il examine la perception visuelle et l'apprentissage dans les cerveaux biologiques et les réseaux neuronaux artificiels. Il utilise l'apprentissage profond comme cadre informatique pour modéliser l'apprentissage et la perception dans le cerveau, et tire parti de notre compréhension du système nerveux pour créer une intelligence artificielle d'inspiration plus biologique.

Étudiants actuels

Peter Brotherwood Brotherwood
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Ian Charest
Site web
Github
Google Scholar
Sevim Caliskan
Collaborateur·rice de recherche
Github
LinkedIn
Laura Chen
Stagiaire de recherche - McGill University
Nastaran Darjani
Doctorat - UdeM
Github
LinkedIn
Google Scholar
Parastoo Geranmayeh
Collaborateur·rice de recherche - Concordia University
Hafez Ghaemi
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Eilif B. Muller
Site web
Github
Google Scholar
Imane Hamzaoui
Doctorat
Google Scholar
Pelin Moradi Haghgou
Stagiaire de recherche - UdeM
Anh Thi Nguyen
Baccalauréat - UdeM
Ladan Shahshahani
Postdoctorat - UdeM
Github
Google Scholar
Liza Sycheva
Maîtrise recherche - UdeM
Doris Voina
Postdoctorat - UdeM
Charlotte Volk
Doctorat - McGill
Superviseur⋅e principal⋅e :
Blake Richards
Github

Publications

The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning
Shahab Bakhtiari
Patrick Mineault
Tim Lillicrap
Christopher C. Pack
Blake A. Richards
The visual system of mammals is comprised of parallel, hierarchical specialized pathways. Different pathways are specialized in so far as th… (voir plus)ey use representations that are more suitable for supporting specific downstream behaviours. In particular, the clearest example is the specialization of the ventral (“what”) and dorsal (“where”) pathways of the visual cortex. These two pathways support behaviours related to visual recognition and movement, respectively. To-date, deep neural networks have mostly been used as models of the ventral, recognition pathway. However, it is unknown whether both pathways can be modelled with a single deep ANN. Here, we ask whether a single model with a single loss function can capture the properties of both the ventral and the dorsal pathways. We explore this question using data from mice, who like other mammals, have specialized pathways that appear to support recognition and movement behaviours. We show that when we train a deep neural network architecture with two parallel pathways using a self-supervised predictive loss function, we can outperform other models in fitting mouse visual cortex. Moreover, we can model both the dorsal and ventral pathways. These results demonstrate that a self-supervised predictive learning approach applied to parallel pathway architectures can account for some of the functional specialization seen in mammalian visual systems.
2021-11-08
NeurIPS.cc/2021/Conference (spotlight)
doi.org
openreview.net
Parallel inference of hierarchical latent dynamics in two-photon calcium imaging of neuronal populations
Luke Y. Prince
Shahab Bakhtiari
Colleen J. Gillon
Blake A. Richards
Dynamic latent variable modelling has provided a powerful tool for understanding how populations of neurons compute. For spiking data, such … (voir plus)latent variable modelling can treat the data as a set of point-processes, due to the fact that spiking dynamics occur on a much faster timescale than the computational dynamics being inferred. In contrast, for other experimental techniques, the slow dynamics governing the observed data are similar in timescale to the computational dynamics that researchers want to infer. An example of this is in calcium imaging data, where calcium dynamics can have timescales on the order of hundreds of milliseconds. As such, the successful application of dynamic latent variable modelling to modalities like calcium imaging data will rest on the ability to disentangle the deeper- and shallower-level dynamical systems’ contributions to the data. To-date, no techniques have been developed to directly achieve this. Here we solve this problem by extending recent advances using sequential variational autoencoders for dynamic latent variable modelling of neural data. Our system VaLPACa (Variational Ladders for Parallel Autoencoding of Calcium imaging data) solves the problem of disentangling deeper- and shallower-level dynamics by incorporating a ladder architecture that can infer a hierarchy of dynamical systems. Using some built-in inductive biases for calcium dynamics, we show that we can disentangle calcium flux from the underlying dynamics of neural computation. First, we demonstrate with synthetic calcium data that we can correctly disentangle an underlying Lorenz attractor from calcium dynamics. Next, we show that we can infer appropriate rotational dynamics in spiking data from macaque motor cortex after it has been converted into calcium fluorescence data via a calcium dynamics model. Finally, we show that our method applied to real calcium imaging data from primary visual cortex in mice allows us to infer latent factors that carry salient sensory information about unexpected stimuli. These results demonstrate that variational ladder autoencoders are a promising approach for inferring hierarchical dynamics in experimental settings where the measured variable has its own slow dynamics, such as calcium imaging data. Our new, open-source tool thereby provides the neuroscience community with the ability to apply dynamic latent variable modelling to a wider array of data modalities.
2021-03-07
BioRxiv (prépublication)
doi.org
Your head is there to move you around: Goal-driven models of the primate dorsal pathway
Patrick J Mineault
Shahab Bakhtiari
Blake A Richards
Christopher C Pack
Neurons in the dorsal visual pathway of the mammalian brain are selective for motion stimuli, with the complexity of stimulus representation… (voir plus)s increasing along the hierarchy. This progression is similar to that of the ventral visual pathway, which is well characterized by artificial neural networks (ANNs) optimized for object recognition. In contrast, there are no image-computable models of the dorsal stream with comparable explanatory power. We hypothesized that the properties of dorsal stream neurons could be explained by a simple learning objective: the need for an organism to orient itself during self-motion. To test this hypothesis, we trained a 3D ResNet to predict an agent’s self-motion parameters from visual stimuli in a simulated environment. We found that the responses in this network accounted well for the selectivity of neurons in a large database of single-neuron recordings from the dorsal visual stream of non-human primates. In contrast, ANNs trained on an action recognition dataset through supervised or self-supervised learning could not explain responses in the dorsal stream, despite also being trained on naturalistic videos with moving objects. These results demonstrate that an ecologically relevant cost function can account for dorsal stream properties in the primate brain.
2020-12-31
Advances in Neural Information Processing Systems 34 (NeurIPS 2021) (publié)
doi.org
openreview.net