Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Detorakis, Georgios Is."'
Autor:
Detorakis, Georgios Is.
Deep learning has become a popular tool across many scientific fields, including the study of differential equations, particularly partial differential equations. This work introduces the basic principles of deep learning and the Deep Galerkin method
Externí odkaz:
http://arxiv.org/abs/2408.11266
Autor:
Dutta, Sourav, Detorakis, Georgios, Khanna, Abhishek, Grisafe, Benjamin, Neftci, Emre, Datta, Suman
Many real-world mission-critical applications require continual online learning from noisy data and real-time decision making with a defined confidence level. Probabilistic models and stochastic neural networks can explicitly handle uncertainty in da
Externí odkaz:
http://arxiv.org/abs/2102.10477
We propose a variation of the self organizing map algorithm by considering the random placement of neurons on a two-dimensional manifold, following a blue noise distribution from which various topologies can be derived. These topologies possess rando
Externí odkaz:
http://arxiv.org/abs/2011.09534
Autor:
Detorakis, Georgios, Dutta, Sourav, Khanna, Abhishek, Jerry, Matthew, Datta, Suman, Neftci, Emre
Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are sufficient operatio
Externí odkaz:
http://arxiv.org/abs/1910.12316
Neural networks are commonly trained to make predictions through learning algorithms. Contrastive Hebbian learning, which is a powerful rule inspired by gradient backpropagation, is based on Hebb's rule and the contrastive divergence algorithm. It op
Externí odkaz:
http://arxiv.org/abs/1806.07406
Autor:
Detorakis, Georgios, Sheik, Sadique, Augustine, Charles, Paul, Somnath, Pedroni, Bruno U., Dutt, Nikil, Krichmar, Jeffrey, Cauwenberghs, Gert, Neftci, Emre
Embedded, continual learning for autonomous and adaptive behavior is a key application of neuromorphic hardware. However, neuromorphic implementations of embedded learning at large scales that are both flexible and efficient have been hindered by a l
Externí odkaz:
http://arxiv.org/abs/1709.10205
Autor:
Rougier, Nicolas P., Hinsen, Konrad, Alexandre, Frédéric, Arildsen, Thomas, Barba, Lorena, Benureau, Fabien C. Y., Brown, C. Titus, de Buyl, Pierre, Caglayan, Ozan, Davison, Andrew P., Delsuc, Marc André, Detorakis, Georgios, Diem, Alexandra K., Drix, Damien, Enel, Pierre, Girard, Benoît, Guest, Olivia, Hall, Matt G., Henriques, Rafael Neto, Hinaut, Xavier, Jaron, Kamil S, Khamassi, Mehdi, Klein, Almar, Manninen, Tiina, Marchesi, Pietro, McGlinn, Dan, Metzner, Christoph, Petchey, Owen L., Plesser, Hans Ekkehard, Poisot, Timothée, Ram, Karthik, Ram, Yoav, Roesch, Etienne, Rossant, Cyrille, Rostami, Vahid, Shifman, Aaron, Stachelek, Joseph, Stimberg, Marcel, Stollmeier, Frank, Vaggi, Federico, Viejo, Guillaume, Vitay, Julien, Vostinar, Anya, Yurchak, Roman, Zito, Tiziano
Publikováno v:
PeerJ Computer Science 3:e142 (2017)
Computer science offers a large set of tools for prototyping, writing, running, testing, validating, sharing and reproducing results, however computational science lags behind. In the best case, authors may provide their source code as a compressed a
Externí odkaz:
http://arxiv.org/abs/1707.04393
An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful ap
Externí odkaz:
http://arxiv.org/abs/1612.05596
Autor:
Pedroni, Bruno U., Sheik, Sadique, Joshi, Siddharth, Detorakis, Georgios, Paul, Somnath, Augustine, Charles, Neftci, Emre, Cauwenberghs, Gert
Spike-timing-dependent plasticity (STDP) incurs both causal and acausal synaptic weight updates, for negative and positive time differences between pre-synaptic and post-synaptic spike events. For realizing such updates in neuromorphic hardware, curr
Externí odkaz:
http://arxiv.org/abs/1607.03070
Extracellular recordings with multi-electrode arrays is one of the basic tools of contemporary neuroscience. These recordings are mostly used to monitor the activities, understood as sequences of emitted action potentials, of many individual neurons.
Externí odkaz:
http://arxiv.org/abs/1412.6383