AI Seminar Series 2022: Alessandro Ingrosso

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On April 29, Alessandro Ingrosso, senior postdoctoral fellow at the Abdus Salam International Centre for Theoretical Physics, presented "Data-Driven Emergence of Convolutional Structure in Neural Networks" at the AI Seminar.

Exploiting invariances in the inputs is crucial for constructing efficient representations and accurate predictions in neural circuits. In neuroscience, translation invariance is at the heart of models of the visual system, while convolutional neural networks designed to exploit translation invariance triggered the first wave of deep learning successes. While the hallmark of convolutions, namely localized receptive fields that tile the input space, can be implemented with fully-connected neural networks, learning convolutions directly from inputs in a fully-connected network has so far proven elusive. In his seminar, Ingrosso discusses how initially fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs, resulting in localized, space-tiling receptive fields. Both translation invariance and non-trivial higher-order statistics are needed to learn convolutions from scratch. He further provides an analytical and numerical characterization of the pattern-formation mechanism responsible for this phenomenon in a simple model, which results in an unexpected link between receptive field formation and the tensor decomposition of higher-order input correlations.

Watch the full presentation below:

Keep up-to-date on the AI Seminar Series by signing up for the mailing list.

Learn how Amii advances world-leading artificial intelligence and machine learning research: visit our Research page.