Jayanth Koushik

I am a PhD student at Carnegie Mellon University studying neural computation and machine learning. I am advised by Mike Tarr and Aarti Singh.

Publications and Preprints

Hypothesis Transfer Learning via Transformation Functions
Simon S. Du, Jayanth Koushik, Aarti Singh, Barnabás Póczos

Improving Stochastic Gradient Descent with Feedback
Jayanth Koushik*, Hiroaki Hayashi*
[arxiv] [code] [poster]

Deep Multimodal Fusion for Persuasiveness Prediction
Behnaz Nojavanasghari*, Deepak Gopinath*, Jayanth Koushik*, Tadas Baltrušaitis, Louis-Philippe Morency
ICMI 2016

* Equal contribution


  • neural-style: Theano/Keras implementation of style transfer algorithms [project] [code]
  • Understanding Convolutional Neural Networks [arxiv]


  • Multiple Perspectives on Linear Regression [pdf]
  • Deriving the Backpropagation Equations [pdf]