Yash Mehta's Website

HHMI Janelia Research Campus.

profile_pic.jpg

Located in Virginia, USA

Hi! I’m a researcher working at the intersection of deep learning and neuroscience at the Funke Lab, HHMI Janelia Research Campus. I’m working on meta-learning biologically plausible plasticity rules in a connectome constraint neural network model.

I am very fortunate to have gotten the opportunity to work with brilliant researchers, who have really inspired me and shaped my attitude towards research. I have worked on Neural Architecture Search with Prof Frank Hutter (ELLIS Fellow) in the most lovely town of Freiburg! Before that, I had an amazing time at the Gatsby Computational Neuroscience Unit at UCL, where I was working on evaluating biologically plausible perturbation-based learning algorithms to train deep networks under the guidance of Prof Peter Latham (Gatsby, UCL) and Tim Lillicrap (DeepMind). My undergraduate thesis on deep learning-based personality prediction with Prof Erik Cambria (NTU SIngapore) is what got me fired up about research in the first place, eventually leading to quit my job at Amazon and dive into research full time ;)

I thoroughly enjoy coding and working on hard algorithmic problems.

News

Oct 1, 2022 Visiting Larry Abbott’s lab in Columbia
Sep 14, 2022 Manuscript on Node Perturbation learning accepted to NeurIPS!
May 27, 2022 Got Married! :ring: :sparkles: :sunny:
Apr 25, 2022 Virtually presented our paper, NAS-Bench-Suite poster at ICLR
Jan 10, 2022 Started at Janelia Research Campus in the Funke Lab

Selected Publications

  1. Stability and Scalability of Node Perturbation Learning
    Naoki Hiratani, Yash MehtaTimothy Lillicrap, and Peter Latham
    In Advances in Neural Information Processing Systems (NeurIPS) 2022
  2. NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy
    Yash Mehta, Colin White, Arber Zela, Arjun Krishnakumar, and 5 more authors
    In International Conference on Learning Representations (ICLR) 2022
  3. Towards Biologically Plausible Convolutional Networks
    Roman Pogodin, Yash MehtaTimothy Lillicrap, and Peter Latham
    In Advances in Neural Information Processing Systems (NeurIPS) 2021