Search Results for author:
Found 8 papers, 3 papers with code
Using evolutionary computation to optimize task performance of unclocked, recurrent Boolean circuits in FPGAs
In one type of implementation the output nodes are used directly to perform a task and all learning is via evolution of the network's node functions.
EM and XRM Connectomics Imaging and Experimental Metadata Standards
These datasets are derived from an increasing number of species, in an increasing number of brain regions, and with an increasing number of techniques.
A Maturity Model for Operations in Neuroscience Research
We propose establishing a five-level capability maturity model for operations in neuroscience research.
Exploiting Large Neuroimaging Datasets to Create Connectome-Constrained Approaches for more Robust, Efficient, and Adaptable Artificial Intelligence
We envision a pipeline to utilize large neuroimaging datasets, including maps of the brain which capture neuron and synapse connectivity, to improve machine learning approaches.
MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction
To bridge this gap, we introduce a new dataset, annotations, and multiple downstream tasks that provide diverse ways to readout information about brain structure and architecture from the same image.
Continual learning benefits from multiple sleep mechanisms: NREM, REM, and Synaptic Downscaling
While some catastrophic forgetting persisted over the course of network training, higher levels of synaptic downscaling lead to better retention of early tasks and further facilitated the recovery of early task accuracy during subsequent training.
L2Explorer: A Lifelong Reinforcement Learning Assessment Environment
Despite groundbreaking progress in reinforcement learning for robotics, gameplay, and other complex domains, major challenges remain in applying reinforcement learning to the evolving, open-world problems often found in critical application spaces.
Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction
State-of-the-art methods for self-supervised learning (SSL) build representations by maximizing the similarity between different transformed "views" of a sample.
