362 citations · 636 across the 5 of their papers we have counts for
5 papers
Successor Feature Sets: Generalizing Successor Representations Across Policies
Kianté Brantley, Soroush Mehri, Geoffrey J. Gordon
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 bee…
Rapid Adaptation with Conditionally Shifted Neurons
Tsendsuren Munkhdalai, Xingdi Yuan, Soroush Mehri +1
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 conditionall…
Deep Complex Networks
Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang +7
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 r…
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
Soroush Mehri, Kundan Kumar, Ishaan Gulrajani +5
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 memor…
On Binary Classification with Single-Layer Convolutional Neural Networks
Soroush Mehri
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 ar…