Bahareh Tolooshams
Bahareh Tolooshams

Postdoctoral Researcher,
CMS Department,
Caltech

Our knowledge can only be finite, while our ignorance must necessarily be infinite.
- Karl Popper

Talks & Workshops
  1. Generative AI and representation learning for inverse problems
    Electrical Engineering & Computer Science Department, York University, 2024 (upcoming)
  2. Sparse autoencoders for gaining mechanistic interpretability of neural signals
    Chen Institute Workshop on AI for Neuro: How Modern AI Technologies Enable Advances in Neuroscience, Caltech, 2024
  3. Understanding the role of feedback in vision systems
    Department of the Navy, Office of Naval Research, 2024
  4. A feedback mechanism in deep generative networks to remove degradation from visual stimuli
    From Neuroscience to Artificially Intelligent Systems (NAISys), Cold Spring Harbor Laboratory, 2024
  5. A feedback mechanism in deep generative networks to remove degradation from visual stimuli
    Swartz Foundation Meeting, University of Washington, 2024
  6. Neural operators for functional ultrasound imaging
    Andersen Lab, Caltech, 2024
  7. AI-powered neuroimaging for brain-computer interfaces
    IST Council at Caltech, 2024
  8. Deep unrolling for inverse problems in engineering and science
    Decision Theory - APMTH 231, Harvard University, 2024
  9. Deep unrolling for inverse problems in engineering and science
    Department of Biomedical Data Science, Stanford University, 2024
  10. Deep interpretable generative learning for science and engineering
    Rising Stars at the Conference on Parsimony and Learning (CPAL), 2024
  11. Deep interpretable generative learning for science and engineering
    Rising Stars in Data Science, University of Chicago, 2023
  12. Generative models for learning interpretable representations of neural data
    MetaConscious Group, MIT, 2023
  13. Design deep neural architectures based on dictionary learning
    Decision Theory - APMTH 231, Harvard University, 2023
  14. Deep learning for inverse problems in engineering and science
    Department of Management Sciences, University of Waterloo, 2023
  15. Interpretable deep learning for deconvolution of multiplexed neural signals
    Computational and Systems Neuroscience (COSYNE), 2023 [talk]
  16. Deep learning for inverse problems in engineering and science
    Healthy ML Group, MIT, 2023
  17. Deep learning for inverse problems in engineering and science
    Department of Electrical and Computer Engineering, University of Waterloo, 2023
  18. Deep learning for inverse problems in engineering and science
    My PhD Defense, Harvard University, 2023
  19. Interpretable multimodal deconvolutional representation learning
    MURI annual meetings, ARL, 2023
  20. Deep representation learning for computational neuroscience
    DiCarlo Lab, MIT, 2022
  21. Interpretable unrolled dictionary learning networks
    Conference on the Mathematical Theory of Deep Neural Networks (DeepMath), 2022
  22. Design interpretable and efficient neural architectures for science and engineering
    Anima AI + Science Lab, Caltech, 2022
  23. Deconvolution of multiplexed neural signals using interpretable deep learning
    Uchida Lab, Harvard University, 2022
  24. Deep unrolled learning using bilevel optimizations
    Vector Institute, 2022
  25. Deep unrolling for inverse problems
    Poggio Lab, MIT, 2021
  26. Unfolded neural networks for implicit acceleration of dictionary learning
    Amirkabir Artificial Intelligence Student Summit (AAISS), Amirkabir University of Technology, 2021
  27. Perceptual stereo speech enhancement
    Applied Sciences Group, Microsoft, 2021
  28. Model-based deep learning
    IEEE ICASSP Conference Tutorial Session, 2021
  29. Introduction to deep learning for computational neuroscience
    Neurosur Workshop, 2021 [github]
  30. Dictionary learning based autoencoders for inverse problems
    Decision Theory - APMTH 231, Harvard University, 2021
  31. On the relationship between dictionary learning and sparse autoencoders
    Computational and Applied Math Seminar, Tufts University, 2020
  32. On the relationship between dictionary learning and sparse autoencoders
    Pierre E. Jacob's Group, Harvard University, 2020
  33. Multichannel end-to-end neural architectures for speech enhancement
    Amazon AI - AWS, 2019
  34. Autoencoders for unsupervised source separation
    Decision Theory - APMTH 231, Harvard University, 2019
  35. State-space models and deep deconvolutional networks
    CRISP Group, Harvard University, 2018