Anand Gopalakrishnan

I am a PhD student with Prof. Jürgen Schmidhuber at The Swiss AI Lab (IDSIA). Previously, I received my masters degree in Electrical Engineering from Pennsylvania State University and my bachelors degree in Electrical and Electronics Engineering from National Institute of Technology Karnataka (NITK). I have been a research intern at The University of Waterloo, Indian Institute of Science and AWS AI Labs.

My research is broadly centered around deep learning and representation learning with a focus on modularity and compositionality.Psychological studies, cognitive and neuroscientific theories on aspects of human perception like attentional gaze, saliency, object perception, binding, relational reasoning, categorization etc. inform my design of computational models. I’m deeply fascinated by both natural and artificial intelligence and wish to distill the essential computational principles from the human mind to build more human-like AI.

My overarching goal is to design a learning system that can discover abstractions and rich structure with the efficiency and generality comparable to how the human mind constructs mental models from direct experience to support goal-directed behavior. My PhD work has focussed on learning structured representations (objects and relations) from high-dimensional perceptual inputs such as images, videos, music, behavioral sequences etc. in a fully unsupervised manner.