Interaction Primitives library

Public Repository for Bensmaia Lab

Unsupervised Domain Adaptation Papers and Code

companion code for "The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Nongaussian Observation Models"

Official repository for the paper "ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation"

Train generalizable policies for kit assembly with self-supervised dense correspondence training.

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

Robot path planning, mapping and exploration algorithms

multineuron spike train kernel

M Beyeler*, EL Rounds*, KD Carlson, N Dutt, JL Krichmar (2019). Neural correlates of sparse coding and dimensionality reduction. PLOS Computational Biology 15(6): e1006908. (*equal contribution)

Awesome Incremental Learning

Awesome work on hand pose estimation/tracking

A curated list of awesome self-supervised methods

Code for "Low-rank discriminant embedding for multiview learning" published on IEEE TCYB

Heterogeneous domain adaptation through progressive alignment, TNNLS

Code for "Transfer Independently Together: A Generalized Framework for Domain Adaptation" published on IEEE TCYB

Locality Preserving Joint Transfer for Domain Adaptation, TIP 2019

[CVPR 2019] Connecting Touch and Vision via Cross-Modal Prediction

Factored-form (square-root) discrete-time Kalman filter implementation methods

TensorLy: Tensor Learning in Python.

Python Implementation of Reinforcement Learning: An Introduction

High-speed simulator of convolutional spiking neural networks with at most one spike per neuron.

Example implementations for paper "Projections for Approximate Policy Iteration" paper

Python and MATLAB code for Stein Variational sampling methods

The source code for Wärnberg & Kumar, Perturbing Low Dimensional Activity Manifolds in Spiking Neuronal Networks, 2019, PLoS Computational Biology

Collection of reproducible deep learning for compressive sensing

Personal website