Zobrazeno 1 - 10
of 12 155
pro vyhledávání: '"CLARK, DAVID"'
Autor:
Clark, David G., Sompolinsky, Haim
Statistical physics provides tools for analyzing high-dimensional problems in machine learning and theoretical neuroscience. These calculations, particularly those using the replica method, often involve lengthy derivations that can obscure physical
Externí odkaz:
http://arxiv.org/abs/2412.01110
We develop a theory to analyze how structure in connectivity shapes the high-dimensional, internally generated activity of nonlinear recurrent neural networks. Using two complementary methods -- a path-integral calculation of fluctuations around the
Externí odkaz:
http://arxiv.org/abs/2409.01969
Autor:
Blackwell, Daniel, Clark, David
In this paper, we introduce an approach for improving the early exploration of grey-box fuzzing campaigns; allowing the fuzzer to reach the interesting coverage earlier. To do this, it leverages information from the system under test's (SUT's) contro
Externí odkaz:
http://arxiv.org/abs/2404.18887
Autor:
Clark, David G., Beiran, Manuel
Neural circuits are composed of multiple regions, each with rich dynamics and engaging in communication with other regions. The combination of local, within-region dynamics and global, network-level dynamics is thought to provide computational flexib
Externí odkaz:
http://arxiv.org/abs/2402.12188
A hot fix is an unplanned improvement to a specific time-critical issue deployed to a software system in production. While hot fixing is an essential and common activity in software maintenance, it has never been surveyed as a research activity. Thus
Externí odkaz:
http://arxiv.org/abs/2401.09275