Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Krishnamurthy, Kamesh"'
Autor:
Webb, Taylor W., Frankland, Steven M., Altabaa, Awni, Segert, Simon, Krishnamurthy, Kamesh, Campbell, Declan, Russin, Jacob, Giallanza, Tyler, Dulberg, Zack, O'Reilly, Randall, Lafferty, John, Cohen, Jonathan D.
A central challenge for cognitive science is to explain how abstract concepts are acquired from limited experience. This has often been framed in terms of a dichotomy between connectionist and symbolic cognitive models. Here, we highlight a recently
Externí odkaz:
http://arxiv.org/abs/2309.06629
Autor:
Bonnaire, Tony, Ghio, Davide, Krishnamurthy, Kamesh, Mignacco, Francesca, Yamamura, Atsushi, Biroli, Giulio
In these lecture notes we present different methods and concepts developed in statistical physics to analyze gradient descent dynamics in high-dimensional non-convex landscapes. Our aim is to show how approaches developed in physics, mainly statistic
Externí odkaz:
http://arxiv.org/abs/2308.03754
Understanding how the dynamics in biological and artificial neural networks implement the computations required for a task is a salient open question in machine learning and neuroscience. In particular, computations requiring complex memory storage a
Externí odkaz:
http://arxiv.org/abs/2307.06398
Autor:
Webb, Taylor W., Frankland, Steven M., Altabaa, Awni, Segert, Simon, Krishnamurthy, Kamesh, Campbell, Declan, Russin, Jacob, Giallanza, Tyler, O’Reilly, Randall, Lafferty, John, Cohen, Jonathan D.
Publikováno v:
In Trends in Cognitive Sciences September 2024 28(9):829-843
Autor:
Can, Tankut, Krishnamurthy, Kamesh
The ability to store continuous variables in the state of a biological system (e.g. a neural network) is critical for many behaviours. Most models for implementing such a memory manifold require hand-crafted symmetries in the interactions or precise
Externí odkaz:
http://arxiv.org/abs/2109.03879
Recurrent neural networks (RNNs) are powerful dynamical models, widely used in machine learning (ML) and neuroscience. Prior theoretical work has focused on RNNs with additive interactions. However, gating - i.e. multiplicative - interactions are ubi
Externí odkaz:
http://arxiv.org/abs/2007.14823
Recurrent neural networks (RNNs) are powerful dynamical models for data with complex temporal structure. However, training RNNs has traditionally proved challenging due to exploding or vanishing of gradients. RNN models such as LSTMs and GRUs (and th
Externí odkaz:
http://arxiv.org/abs/2002.00025
Autor:
Krishnamurthy, Kamesh, Hermundstad, Ann M, Mora, Thierry, Walczak, Aleksandra M, Balasubramanian, Vijay
Animals smelling in the real world use a small number of receptors to sense a vast number of natural molecular mixtures, and proceed to learn arbitrary associations between odors and valences. Here, we propose a new interpretation of how the architec
Externí odkaz:
http://arxiv.org/abs/1707.01962
Autor:
Krishnamurthy, Kamesh
The field of neurobiology focuses on the development, maintenance, and function of the nervous system. Of particular interest is the formation of synapses, the junctions which allow for transmission and control of information between neurons. Synapse
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.