1.8k citations · 2.9k across the 18 of their papers we have counts for
18 papers
Sample complexity bounds for the Jensen-Shannon divergence
Oren Richter, Adi Ben-Ari, Tom Talpir +1
The Jensen-Shannon divergence (JSD) is a symmetric and bounded measure of the dissimilarity of two probability distributions, which has become a standard tool in statistics, inform…
Identifying structural design principles shaping the computational abilities of recurrent neural networks
Tom Talpir, Elad Schneidman
Understanding how the architecture of neural networks shapes the computations they carry is a central challenge in neuroscience and machine learning. While specific circuit archite…
Semantic representations emerge in biologically inspired ensembles of cross-supervising neural networks
Roy Urbach, Elad Schneidman
Brains learn to represent information from a large set of stimuli, typically by weak supervision. Unsupervised learning is therefore a natural approach for exploring the design of…
The computational and learning benefits of Daleian neural networks
Adam Haber, Elad Schneidman
Dale's principle implies that biological neural networks are composed of neurons that are either excitatory or inhibitory. While the number of possible architectures of such Daleia…
Estimating the Unique Information of Continuous Variables
Ari Pakman, Amin Nejatbakhsh, Dar Gilboa +4
The integration and transfer of information from multiple sources to multiple targets is a core motive of neural systems. The emerging field of partial information decomposition (P…
Probabilistic models of individual and collective animal behavior
Katarina Bodova, Gabriel J. Mitchell, Roy Harpaz +2
Recent developments in automated tracking allow uninterrupted, high-resolution recording of animal trajectories, sometimes coupled with the identification of stereotyped changes of…