Bit-Slicing FPGA Accelerator for Quantized Neural Networks
Posted on03/07/2019
Deep Neural Networks (DNNs) become the state-of-the-art in several domains such as computer vision or speechrecognition. However, using DNNs for embedded applications... Read More
On Relativistic f-Divergences
Posted on01/07/2019
This paper provides a more rigorous look at Relativistic Generative Adversarial Networks (RGANs). We prove that the objective function of the discriminator... Read More
Morphological Irregularity Correlates with Frequency
Posted on27/06/2019
We present a study of morphological irregularity. Following recent work, we define an information-theoretic measure of irregularity based on the predictability of... Read More
Learning Causal State Representations of Partially Observable Environments
Posted on25/06/2019
Intelligent agents can cope with sensory-rich environments by learning task-agnostic state abstractions. In this paper, we propose mechanisms to approximate causal states,... Read More
Neural Transfer Learning for Cry-based Diagnosis of Perinatal Asphyxia
Posted on24/06/2019
Despite continuing medical advances, the rate of newborn morbidity and mortality globally remains high, with over 6 million casualties every year. The... Read More
EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
Posted on19/06/2019
We present the first sentence simplification model that learns explicit edit operations (ADD, DELETE, and KEEP) via a neural programmer-interpreter approach. Most... Read More
Compositional Fairness Constraints for Graph Embeddings
Posted on17/06/2019
Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks... Read More
Learning Powerful Policies by Using Consistent Dynamics Mode
Posted on11/06/2019
Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has... Read More
Learning to evoke complex motor outputs with spatiotemporal neurostimulation using a hierarchical and adaptive optimization algorithm
Posted on11/06/2019
The development of neurostimulation techniques to evoke motor patterns is an active area of research. It serves as a crucial experimental tool... Read More
DeepMDP: Learning Continuous Latent Space Models for Representation Learning
Posted on06/06/2019
Many reinforcement learning (RL) tasks provide the agent with high-dimensional observations that can be simplified into low-dimensional continuous states. To formalize this... Read More