Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Ionescu, Catalin"'
Autor:
Carreira, João, King, Michael, Pătrăucean, Viorica, Gokay, Dilara, Ionescu, Cătălin, Yang, Yi, Zoran, Daniel, Heyward, Joseph, Doersch, Carl, Aytar, Yusuf, Damen, Dima, Zisserman, Andrew
We introduce a framework for online learning from a single continuous video stream -- the way people and animals learn, without mini-batches, data augmentation or shuffling. This poses great challenges given the high correlation between consecutive v
Externí odkaz:
http://arxiv.org/abs/2312.00598
Autor:
Carreira, Joao, Koppula, Skanda, Zoran, Daniel, Recasens, Adria, Ionescu, Catalin, Henaff, Olivier, Shelhamer, Evan, Arandjelovic, Relja, Botvinick, Matt, Vinyals, Oriol, Simonyan, Karen, Zisserman, Andrew, Jaegle, Andrew
General perception systems such as Perceivers can process arbitrary modalities in any combination and are able to handle up to a few hundred thousand inputs. They achieve this generality by using exclusively global attention operations. This however
Externí odkaz:
http://arxiv.org/abs/2202.10890
Autor:
Jaegle, Andrew, Borgeaud, Sebastian, Alayrac, Jean-Baptiste, Doersch, Carl, Ionescu, Catalin, Ding, David, Koppula, Skanda, Zoran, Daniel, Brock, Andrew, Shelhamer, Evan, Hénaff, Olivier, Botvinick, Matthew M., Zisserman, Andrew, Vinyals, Oriol, Carreira, Joāo
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied beyond a small set of stereotyped settings, as they bake in domain &
Externí odkaz:
http://arxiv.org/abs/2107.14795
Reinforcement learning (RL) combines a control problem with statistical estimation: The system dynamics are not known to the agent, but can be learned through experience. A recent line of research casts `RL as inference' and suggests a particular fra
Externí odkaz:
http://arxiv.org/abs/2001.00805
Autor:
Kulkarni, Tejas, Gupta, Ankush, Ionescu, Catalin, Borgeaud, Sebastian, Reynolds, Malcolm, Zisserman, Andrew, Mnih, Volodymyr
The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object r
Externí odkaz:
http://arxiv.org/abs/1906.11883
Autor:
Warde-Farley, David, Van de Wiele, Tom, Kulkarni, Tejas, Ionescu, Catalin, Hansen, Steven, Mnih, Volodymyr
Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specif
Externí odkaz:
http://arxiv.org/abs/1811.11359
Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, output
Externí odkaz:
http://arxiv.org/abs/1610.06258
Deep neural network architectures have recently produced excellent results in a variety of areas in artificial intelligence and visual recognition, well surpassing traditional shallow architectures trained using hand-designed features. The power of d
Externí odkaz:
http://arxiv.org/abs/1509.07838
Autor:
Cîmpan, Marius1 marius.cimpan@rcc.ro, Pacuraru-Ionescu, Catalin-Paul2 paul@pacuraru.com, Borlea, Sorin Nicolae3 snborlea@yahoo.com, Jansen, Adela4 jansen.adela@yahoo.com
Publikováno v:
Proceedings of the International Conference on Business Excellence. 2023, Vol. 17 Issue 1, p2036-2052. 17p.
Autor:
LUNGU, Bianca Cornelia, IONESCU, Catalin, TUDOR, Beatrice Ana-Maria, GEORGESCU, Ovidiu Ionut, MIRCU, Calin, HUTU, Ioan
Publikováno v:
Lucrari Stiintifice: Seria Medicina Veterinara; 2022, Vol. 65 Issue 3, p13-16, 4p