Book: Sparse Modeling: Theory, Algorithms and Applications
Posted on02/12/2019
Sparse models are particularly useful in scientific applications, such as biomarker discovery in genetic or neuroimaging data, where the interpretability of a... Read More
Attention based pruning for shift networks
Posted on20/11/2019
In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, it... Read More
Leveraging exploration in off-policy algorithms via normalizing flows
Posted on24/10/2019
The ability to discover approximately optimal policies in domains with sparse rewards is crucial to applying reinforcement learning (RL) in many realworld... Read More
Transferable Neural Projection Representations
Posted on16/09/2019
Neural word representations are at the core of many state-of-the-art natural language processing models. A widely used approach is to pre-train, store... Read More
Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies
Posted on16/09/2019
Modelling long-term dependencies is a challenge for recurrent neural networks. This is primarily due to the fact that gradients vanish during training,... Read More
TaskMaster-1 Dialog Corpus: Toward a Realistic and Diverse Dataset
Posted on16/09/2019
A significant barrier to progress in data-driven approaches to building dialog systems is the lack of high quality, goal-oriented conversational data. To... Read More
Deep Reinforcement Learning For Modeling Chit-Chat Dialog With Discrete Attributes
Posted on16/09/2019
Open domain dialogues face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that we are able... Read More
Generalized Denoising Auto-Encoders as Generative Models
Posted on14/08/2019
Recent work has shown how denoising and contractive autoencoders implicitly capture the structure of the data-generating density, in the case where the... Read More
U-Net Fixed-Point Quantization for Medical Image Segmentation
Posted on02/08/2019
Model quantization is leveraged to reduce the memory consumption and the computation time of deep neural networks. This is achieved by representing... Read More
Systematic Generalization: What Is Required and Can It Be Learned?
Posted on05/07/2019
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given... Read More