Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Mehri, Soroush"'
Successor-style representations have many advantages for reinforcement learning: for example, they can help an agent generalize from past experience to new goals, and they have been proposed as explanations of behavioral and neural data from human an
Externí odkaz:
http://arxiv.org/abs/2103.02650
Neural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks. Minority examples, i.e., examples that contradict the spurious correlations present in the majority of data points, have been shown to i
Externí odkaz:
http://arxiv.org/abs/1911.03861
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework of metalea
Externí odkaz:
http://arxiv.org/abs/1712.09926
Autor:
Trabelsi, Chiheb, Bilaniuk, Olexa, Zhang, Ying, Serdyuk, Dmitriy, Subramanian, Sandeep, Santos, João Felipe, Mehri, Soroush, Rostamzadeh, Negar, Bengio, Yoshua, Pal, Christopher J
At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on recurrent neural networks and older fundamental theoretical analysis su
Externí odkaz:
http://arxiv.org/abs/1705.09792
Autor:
Mehri, Soroush, Kumar, Kundan, Gulrajani, Ishaan, Kumar, Rithesh, Jain, Shubham, Sotelo, Jose, Courville, Aaron, Bengio, Yoshua
In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time. We show that our model, which profits from combining memory-less modules, namely autoregressive multilayer perceptrons, and stat
Externí odkaz:
http://arxiv.org/abs/1612.07837
Autor:
Mehri, Soroush
Convolutional neural networks are becoming standard tools for solving object recognition and visual tasks. However, most of the design and implementation of these complex models are based on trail-and-error. In this report, the main focus is to consi
Externí odkaz:
http://arxiv.org/abs/1509.03891
Autor:
Gohari Boroujerdi, Emad, Mehri, Soroush, Sadeghi Garmaroudi, Saeed, Pezeshki, Mohammad, Rashidi Mehrabadi, Farid, Malakouti, SeyyedSalim, Khadivi, Shahram
Publikováno v:
2014 6th Conference on Information & Knowledge Technology (IKT); 2014, p61-66, 6p
