����ֱ��

This collection of repositories consists of highly configurable environments for developing reinforcement learning agents that continually learn, as well as metrics for continual learning.

SABER (Scalable Analytics for Brain Exploration Research) is a library of containerized tools and a workflow deployment system for enabling processing of large neuroimaging datasets.

This repository is meant to include code supporting the paper “Continuous State Estimation from Synapse Constrained Connectivity,” presented at WCCI2022, and available online at IEEE Xplore and arXiv.

A repository to quickly generate synthetic data and associated trojaned deep learning models.

Reconnaissance Blind Chess (RBC) is a chess variant designed for new research in artificial intelligence. RBC includes imperfect information, long-term strategy, explicit observations, and almost no common knowledge. These features appear in real-world scenarios and challenge even state-of-the-art algorithms. Each RBC player controls traditional chess pieces but cannot directly see the locations of their opponent's pieces. Rather, a player learns partial information each turn by privately sensing a chosen 3×3 area of the board.

Eight high-resolution electron microscopy volumes of C. elegans brains at different stages of development, spanning birth to adulthood.

High-resolution electron microscopy, segmentation, and morphological reconstruction of cortical circuits within the visual cortex of mouse.

Mouse-Dyer3

The images provided are micro-computed tomography data collected from 2-BM at Argonne National Laboratory.

High-resolution electron microscopy, segmentation, and morphological reconstruction of cortical circuits within the visual cortex of mouse.