akjagadish

3D-R2N2

Single/multi view image(s) to voxel reconstruction using a recurrent neural network

3dr2n2-Deep-Learning-Course-project-

Re-implement 3dr2n2 with tensorflow and improve the performance.

akjagadish.github.io

Personal Website

behavior-model-fitting

This repository will include python scripts to fit models, mostly RL models, to (simulated) behavioural data.

causal_neuroscience

Collection of introductory study material for people who are interested to answer causal questions in the field of neuroscience.

deeproad

CVPR 2018 DeepGlobe Road Extraction Challenge

ermi

Ecologically rational meta-learned inference explains human category learning

gpt-trauma-induction

Code for “Chat-GPT on the Couch”: Mitigating State Anxiety in Large Language Models via Mindfulness-based Relaxation Techniques

InContext-Learning-Dynamics

tutorial-metarl

akjagadish/ermi

Ecologically rational meta-learned inference explains human category learning

akjagadish/InContext-Learning-Dynamics

akjagadish/akjagadish.github.io

Personal Website

akjagadish/behavior-model-fitting

This repository will include python scripts to fit models, mostly RL models, to (simulated) behavioural data.

akjagadish/causal_neuroscience

Collection of introductory study material for people who are interested to answer causal questions in the field of neuroscience.

akjagadish/cmr

Project repo for Learning Category-Specific Mesh Reconstruction from Image Collections

akjagadish/gpt-trauma-induction

Code for “Chat-GPT on the Couch”: Mitigating State Anxiety in Large Language Models via Mindfulness-based Relaxation Techniques

akjagadish/reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

akjagadish/tutorial-metarl

akjagadish/compositional-bandits

akjagadish/Compositional_MetaRL

Code for my paper: Meta-Learning of Compositional Task Distributions in Humans and Machines

akjagadish/covasim

COVID-19 Agent-based Simulator (Covasim): a model for understanding novel coronavirus epidemiology

akjagadish/cpilab.github.io

CPILab page

akjagadish/CPPN

Compositional Pattern Producing Networks used at the Brain.io Hackathon, Vienna

akjagadish/docker-ubuntu-vnc-desktop

A Docker image to provide web VNC interface to access Ubuntu LXDE/LxQT desktop environment.

akjagadish/github-slideshow

A robot powered training repository :robot:

akjagadish/GPT3goesPsychology

akjagadish/HeuristicsFromBMLI

akjagadish/intro-html

A robot powered training repository :robot:

akjagadish/ivon

IVON optimizer for neural networks based on variational learning.

akjagadish/Laplace

Laplace approximations for Deep Learning.

akjagadish/ml-agents

Unity Machine Learning Agents Toolkit

akjagadish/nnfabrik

A generalized model fitting pipeline that houses models, trainers, and datasets in datajoint and returns as well as stores trained models.

akjagadish/online-aversive-learning

Code for our study looking at aversive learning online

akjagadish/resource-rational-compositional-RL

Code and Data for "Zero-shot compositional reinforcement learning in humans

akjagadish/StructuredBandits

Hierarchical Bayesian model fitting for "Finding structure in multi-armed bandits"

akjagadish/TDSR

Temporal Difference Successor Representation Model

akjagadish/vanilla-llama

Plain pytorch implementation of LLaMA

akjagadish/website-template

:ramen: Minimalist Jekyll Template, dark and light themes

akjagadish/xland-minigrid

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️