Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Felipe Petroski Such"'
Publikováno v:
AAAI
There is broad interest in creating RL agents that can solve many (related) tasks and adapt to new tasks and environments after initial training. Model-based RL leverages learned surrogate models that describe dynamics and rewards of individual tasks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1bc5ab87fbba59cdd5d4876948adc69
https://doi.org/10.1609/aaai.v34i04.5989
https://doi.org/10.1609/aaai.v34i04.5989
Autor:
Frank Brockler, Raymond Ptucha, Suhas Pillai, Paul Hutkowski, Felipe Petroski Such, Vatsala Singh
Publikováno v:
Pattern Recognition. 88:604-613
The recognition of handwritten text is challenging as there are virtually infinite ways a human can write the same message. Deep learning approaches for handwriting analysis have recently demonstrated breakthrough performance using both lexicon-based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ece1963607eaa7c2bee8a677813af1b8
https://doi.org/10.1016/j.patcog.2018.12.017
https://doi.org/10.1016/j.patcog.2018.12.017
Autor:
Raymond Ptucha, Andrew M. Michael, Chao Zhang, Shagan Sah, Miguel Dominguez, Felipe Petroski Such, Nathan D. Cahill, Suhas Pillai
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 11:884-896
Convolutional Neural Networks (CNNs) have recently led to incredible breakthroughs on a variety of pattern recognition problems. Banks of finite impulse response filters are learned on a hierarchy of layers, each contributing more abstract informatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::588d479dcf29e5585d979669f0d07255
https://doi.org/10.1109/jstsp.2017.2726981
https://doi.org/10.1109/jstsp.2017.2726981
Publikováno v:
ICFHR
Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream of symbol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f179bd6a68e2552a2704ef757fa9348
https://doi.org/10.1109/icfhr-2018.2018.00024
https://doi.org/10.1109/icfhr-2018.2018.00024
Autor:
Jeff Clune, Rosanne Liu, Felipe Petroski Such, Rui Wang, Yulun Li, Marc G. Bellemare, Ludwig Schubert, Jiale Zhi, Pablo Samuel Castro, Vashisht Madhavan, Joel Lehman
Publikováno v:
IJCAI
Much human and computational effort has aimed to improve how deep reinforcement learning algorithms perform on benchmarks such as the Atari Learning Environment. Comparatively less effort has focused on understanding what has been learned by such met
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9bea10f4b1df07065a1ab2a915c46c49
Publikováno v:
ICIP
Voxels are an effective approach to 3D mesh and point cloud classification because they build upon mature Convolutional Neural Network concepts. We show however that their cubic increase in dimensionality is unsuitable for more challenging problems s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2fae7ac8b2b2c9ee4aa7d2c85445e272
https://doi.org/10.1109/icip.2017.8297019
https://doi.org/10.1109/icip.2017.8297019
Publikováno v:
CVPR Workshops
Recent advances in video understanding are enabling incredible developments in video search, summarization, automatic captioning and human computer interaction. Attention mechanisms are a powerful way to steer focus onto different sections of the vid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::67b3097d28aa672e50bc09e26158181f
https://doi.org/10.1109/cvprw.2017.274
https://doi.org/10.1109/cvprw.2017.274