adityagilra Goto Github PK
Name: Aditya Gilra
Type: User
Company: Centrum Wiskunde & Informatica
Bio: Researcher, Machine Learning Group
Location: Amsterdam, Netherlands
Blog: adityagilra.net
Name: Aditya Gilra
Type: User
Company: Centrum Wiskunde & Informatica
Bio: Researcher, Machine Learning Group
Location: Amsterdam, Netherlands
Blog: adityagilra.net
Calculate and plot response of a population of spiking neurons to a constant and a sinusoid riding on top via simulation (brian2) and theory (integral and differential approaches); uses my neurtheor module.
Synthesize bio-plausible neural networks for cognitive tasks, mimicking brain architecture
Deep Deterministic Policy Gradient implemented in PyTorch for DeepMind Control Suite
Feedback-based Online Local Learning Of Weights (FOLLOW)
Motor control using inverse model learned via FOLLOW
Notes / derivations / models from papers that I have read since April 2014.
A toolkit for developing and comparing reinforcement learning algorithms.
Idealized GCM from the University of Exeter
MELD: Meta-Reinforcement Learning from Images via Latent State Models https://arxiv.org/abs/2010.13957
A Python library for creating and simulating large-scale brain models
MPI backend for the nengo neural simulator.
OpenCL-based simulator for Nengo neural models
NeuroTheory: A Python module to compute baseline and linear response of populations of spiking neurons in the integral or differential framework. See Gerstner et al book [ http://neuronaldynamics.epfl.ch/ ] for the spike response model of neurons and related integral approach. See Richardson 2007 [ http://link.aps.org/doi/10.1103/PhysRevE.76.021919 ] for the differential approach on the LIF model.
A detailed network model of part of the rat olfactory bulb comprising compartmental mitral, granule and PG cells developed by Aditya Gilra and Upinder S. Bhalla (Gilra A, Bhalla US (2015) Bulbar Microcircuit Model Predicts Connectivity and Roles of Interneurons in Odor Coding. PLoS ONE 10(5): e0098045.) The cell morphologies and network connections are in NeuroML v1.8.
A Python package for simulator-independent specification of neuronal network models.
Simple python simulator for 'rate neurons' with continuous-valued, rectified output, connected by static/plastic synapses.
Spatio-temporal forecasting of Lorenz96 with RC-ESN, RNN-LSTM and ANN
A simple A2C made from scratch in PyTorch. Accompanying comic at https://hackernoon.com/intuitive-rl-intro-to-advantage-actor-critic-a2c-4ff545978752
An educational resource to help anyone learn deep reinforcement learning.
A repository for control benchmarking code
Provided is the code and accompanying documentation for inferring the parameters (via the Baum-Welch algorithm; see Prentice et al., 2016) of the Tree hidden Markov model (HMM) for neural population spike train data. This version can be used locally directly in Matlab, via mex files, or in Python via `make` using the Makelfile..
Tutorials that I've given as a tutor at computational neuroscience summer schools
Finding or learning latent modes / clusters in neural spiking data
Implementation in C++ (mexed for local callable use in Matlab, now in Python too) of the variational inference winner-take-all neural circuit model for real-time unsupervised clustering.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.