Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Hirak J. Kashyap"'
Autor:
Kexin Chen, Tiffany Hwu, Hirak J. Kashyap, Jeffrey L. Krichmar, Kenneth Stewart, Jinwei Xing, Xinyun Zou
Publikováno v:
Frontiers in Neurorobotics, Vol 14 (2020)
Understanding why deep neural networks and machine learning algorithms act as they do is a difficult endeavor. Neuroscientists are faced with similar problems. One way biologists address this issue is by closely observing behavior while recording neu
Externí odkaz:
https://doaj.org/article/06a3ea86952c475da5bce8b4eb21879f
Autor:
Jeffrey D. Kopsick, Carolina Tecuatl, Keivan Moradi, Sarojini M. Attili, Hirak J. Kashyap, Jinwei Xing, Kexin Chen, Jeffrey L. Krichmar, Giorgio A. Ascoli
Publikováno v:
Cognitive Computation.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c95f06195fd2d81a81915b167b7ad935
https://doi.org/10.1007/s12559-021-09954-2
https://doi.org/10.1007/s12559-021-09954-2
Publikováno v:
IEEE transactions on neural networks and learning systems, vol 32, iss 6
Dynamic scenes that contain both object motion and egomotion are a challenge for monocular visual odometry (VO). Another issue with monocular VO is the scale ambiguity, i.e. these methods cannot estimate scene depth and camera motion in real scale. H
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c6c08d0e9fbac15fe4e3a42d14463574
https://escholarship.org/uc/item/7p53p8zv
https://escholarship.org/uc/item/7p53p8zv
Publikováno v:
IJCNN
A robot operating in multiple settings must develop stable as well as flexible representations of the tasks and contexts associated with their environments. Taking inspiration from neurobiology, we apply a neural network model of schemas and memory c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::596f39b8842d5a3e9cb11fc160fd6d1e
https://doi.org/10.1109/ijcnn48605.2020.9206858
https://doi.org/10.1109/ijcnn48605.2020.9206858
Autor:
Francky Catthoor, Adarsha Balaji, Nikil Dutt, Prathyusha Adiraju, Hirak J. Kashyap, Jeffrey L. Krichmar, Anup Das
Publikováno v:
IJCNN
We present PyCARL, a PyNN-based common Python programming interface for hardware-software co-simulation of spiking neural network (SNN). Through PyCARL, we make the following two key contributions. First, we provide an interface of PyNN to CARLsim, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcc75942340dc0a744412645e850be6c
http://arxiv.org/abs/2003.09696
http://arxiv.org/abs/2003.09696
Publikováno v:
Computer Communications. 110:48-58
A real-time DDoS attack detection method should identify attacks with low computational overhead. Although a large number of statistical methods have been designed for DDoS attack detection, real-time statistical solution to detect DDoS attacks in ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::051021c86aefd268613d169de97e8eb4
https://doi.org/10.1016/j.comcom.2017.05.015
https://doi.org/10.1016/j.comcom.2017.05.015
Autor:
Ricardo Chaves, Hirak J. Kashyap
Publikováno v:
ACM Transactions on Reconfigurable Technology and Systems. 9:1-22
The dynamic partial reconfiguration functionality of FPGAs can be attacked, particularly when the FPGA is remotely located or the configuration bitstreams are sent through insecure networks. The existing FPGA technologies provide some built-in securi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::881a906c087c6bb226fd9ed54722bf43
https://doi.org/10.1145/2816822
https://doi.org/10.1145/2816822
Publikováno v:
IJCNN
A predictive mechanism in the brain enables primates to visually track a target with almost zero lag smooth pursuit eye movements, overcoming the delays in processing retinal inputs. Interestingly, it also allows pursuit of occluded targets with nonl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::311ed20f285f1b307a3bffdebeca596f
https://doi.org/10.1109/ijcnn.2018.8489652
https://doi.org/10.1109/ijcnn.2018.8489652
Autor:
Nikil Dutt, Jinwei Xing, Michael Beyeler, Jeffrey L. Krichmar, Stanislav Listopad, Emily L. Rounds, Ting-Shuo Chou, Hirak J. Kashyap
Publikováno v:
IJCNN
Large-scale spiking neural network (SNN) simulations are challenging to implement, due to the memory and computation required to iteratively process the large set of neural state dynamics and updates. To meet these challenges, we have developed CARLs
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70fbf795cb2241dd44621719f15ca3d2
https://doi.org/10.1109/ijcnn.2018.8489326
https://doi.org/10.1109/ijcnn.2018.8489326
Publikováno v:
CVPR
We introduce a stereo correspondence system implemented fully on event-based digital hardware, using a fully graph-based non von-Neumann computation model, where no frames, arrays, or any other such data-structures are used. This is the first time th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb9fc955df838b7a7327b1585f301ac4
https://doi.org/10.1109/cvpr.2018.00786
https://doi.org/10.1109/cvpr.2018.00786