Talks & Workshops
    Please email me for invited talks.
  • Interpretability in artificial intelligence
    Upper Bound Conference, Edmonton, 2026 (future)
    Technology & the Future of Medicine Course, University of Alberta, 2026 (future)
    Artificial Intelligence Everywhere Course, University of Alberta, 2026
  • Learning interpretable representations in neural signals with sparse autoencoders
    Hotchkiss Brain Institute, University of Calgary, 2026 (future)
    AI/Biology Workshop, Canadian Conference on AI, 2026 (future)
    Computational Machinery of Cognition Lab, Technische Universität Dresden, 2025
    Chen Institute Workshop on AI for Neuro: How Modern AI Technologies Enable Advances in Neuroscience, Caltech, 2024
  • Learning as inference: Inductive bias and the geometry of representations
    Learning as inference: Structure, representation, and interpretability
    Center for Computational Neuroscience, Flatiron Institute, 2026
    Alberta Machine Intelligence Institute (Amii), 2026
  • Sparse autoencoder neural operators: Model recovery in function spaces
    Workshop on Unifying Representations in Neural Models, NeurIPS, 2025
  • From regularization to generation: AI for inverse problems
    CIFAR Deep Learning + Reinforcement Learning Summer School, Amii, 2025
  • Neural operators and biologically-informed latent embeddings for foundation models in neuroAI
    Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences, ICML, 2025
  • Representation learning through the lens of inverse problems in AI and neuroscience
    Electrical & Computer Engineering Department, University of Alberta, 2025
  • Generative AI and representation learning for inverse problems
    Electrical Engineering & Computer Science Department, York University, 2024
  • A feedback mechanism in deep generative networks to remove degradation from visual stimuli
    Understanding the role of feedback in vision systems
    Department of the Navy, Office of Naval Research, 2024
    From Neuroscience to Artificially Intelligent Systems (NAISys), Cold Spring Harbor Laboratory, 2024
    Swartz Foundation Meeting, University of Washington, 2024
  • Neural operators for functional ultrasound imaging
    Andersen Lab, Caltech, 2024
  • AI-powered neuroimaging for brain-computer interfaces
    IST Council at Caltech, 2024
  • Deep unrolling for inverse problems in engineering and science
    Decision Theory - APMTH 231, Harvard University, 2024
    Department of Biomedical Data Science, Stanford University, 2024
    Rising Stars at the Conference on Parsimony and Learning (CPAL), 2024
    Department of Management Sciences, University of Waterloo, 2023
    Healthy ML Group, MIT, 2023
    Rising Stars in Data Science, University of Chicago, 2023
    Department of Electrical and Computer Engineering, University of Waterloo, 2023
    My PhD Defense, Harvard University, 2023
    Anima AI + Science Lab, Caltech, 2022
  • Generative models for learning interpretable representations of neural data
    MetaConscious Group, MIT, 2023
  • Design deep neural architectures based on dictionary learning
    Decision Theory - APMTH 231, Harvard University, 2023
  • Interpretable deep learning for deconvolution of multiplexed neural signals
    Computational and Systems Neuroscience (COSYNE), 2023 [talk]
    Uchida Lab, Harvard University, 2022
  • Interpretable multimodal deconvolutional representation learning
    MURI annual meetings, ARL, 2023
  • Deep representation learning for computational neuroscience
    DiCarlo Lab, MIT, 2022
  • Interpretable unrolled dictionary learning networks
    Conference on the Mathematical Theory of Deep Neural Networks (DeepMath), 2022
  • Deep unrolled learning using bilevel optimizations
    Vector Institute, 2022
  • Deep unrolling for inverse problems
    Poggio Lab, MIT, 2021
  • Unfolded neural networks for implicit acceleration of dictionary learning
    Amirkabir Artificial Intelligence Student Summit (AAISS), Amirkabir University of Technology, 2021
  • Perceptual stereo speech enhancement
    Applied Sciences Group, Microsoft, 2021
  • Model-based deep learning
    IEEE ICASSP Conference Tutorial Session, 2021
  • Introduction to deep learning for computational neuroscience
    Neurosur Workshop, 2021 [github]
  • Dictionary learning based autoencoders for inverse problems
    Decision Theory - APMTH 231, Harvard University, 2021
  • On the relationship between dictionary learning and sparse autoencoders
    Computational and Applied Math Seminar, Tufts University, 2020
    Pierre E. Jacob's Group, Harvard University, 2020
  • Multichannel end-to-end neural architectures for speech enhancement
    Amazon AI - AWS, 2019
  • Autoencoders for unsupervised source separation
    Decision Theory - APMTH 231, Harvard University, 2019
  • State-space models and deep deconvolutional networks
    CRISP Group, Harvard University, 2018