Publications

Transformers, LLMs, Neural Networks, Neuroscience, Cognition

2024

  1. In prep
    ArchVision: How far can you model biological vision solely with architecture and local learning?
    Yash Mehta, Atlas Kazemian, Colin Conwell, and Michael Bonner
    In 2024
  2. In prep
    An Empirical Study of Perturbation Based Algorithms for Training Deep Networks
    Yash Mehta, Naoki Hiratani, Peter Latham, and Timothy Lillicrap
    In 2024

2023

  1. Biorxiv
    Model-Based Inference of Synaptic Plasticity Rules
    Yash Mehta, Dan Tyulmankov, Adithya Rajagopalan, James Fitzgerald, and 1 more author
    In 2023

2022

  1. 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
  2. Stability and Scalability of Node Perturbation Learning
    Naoki Hiratani, Yash MehtaTimothy Lillicrap, and Peter Latham
    In Advances in Neural Information Processing Systems (NeurIPS) 2022
  3. Future-generation personality prediction from digital footprints
    Yash Mehta, Clemens Stachl, Konstantin Markov, Joseph T Yun, and 1 more author
    Future Generation Computer Systems 2022

2021

  1. Towards Biologically Plausible Convolutional Networks
    Roman Pogodin, Yash MehtaTimothy Lillicrap, and Peter Latham
    In Advances in Neural Information Processing Systems (NeurIPS) 2021

2020

  1. Personality Trait Detection Using Bagged SVM over BERT Word Embedding Ensembles
    In ACL WiNLP Workshop 2020
  2. Bottom-Up and Top-Down: Predicting Personality with Psycholinguistic and Language Model Features
    Yash Mehta, Samin Fatehi, Amirmohammad Kazameini, Clemens Stachl, and 1 more author
    In 2020 IEEE International Conference on Data Mining (ICDM) 2020
  3. Multitask learning for emotion and personality detection
    Yang Li, Amirmohammad Kazameini, Yash Mehta, and Erik Cambria
    Neurocomputing 2020

2019

  1. Recent Trends in Deep Learning Based Personality Detection
    Yash Mehta, Navonil Majumder, Alexander Gelbukh, and Erik Cambria
    Artificial Intelligence Review 2019