We describe a simple neural language model that relies only on character-level inputs. Predictions are still made at the word-level. Our model employ…

We consider supervised learning with random decision trees, where the tree construction is completely random. The method is popularly used and works …

Karloff? and Shirley recently proposed summary trees as a new way to visualize large rooted trees (Eurovis 2013) and gave algorithms for generating a…

Topic models provide a useful method for dimensionality reduction and exploratory data analysis in large text corpora. Most approaches to topic model…

This article demontrates that we can apply deep learning to text understanding from character-level inputs all the way up to abstract text concepts, …

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in …

This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture …

In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and se…

Applying deep learning methods to mammography assessment has remained a challenging topic. Dense noise with sparse expressions, mega-pixel raw data r…

Many tasks in AI require the collaboration of multiple agents. Typically, the communication protocol between agents is manually specified and not alt…

We have provided the first effective subdivision algorithm Miranda for isolating simple real roots of a system of equations f=\bf 0, provided f and its derivatives have interval forms. Our result are novel for its completeness (previous algorithms n…

We describe a new algorithm \texttt{Miranda} for isolating the simple zeros of a function $\boldsymbol{f}:{\mathbb R}^n\to{\mathbb R}^n$ within a box…

We present an extensive study of generalization for data-dependent hypothesis sets. We give a general learning guarantee for data-dependent hypothesi…

This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the …

Search strategies for generating a response from a neural dialogue model have received relatively little attention compared to improving network arch…

Improving on the Voronoi cell based techniques of Micciancio and Voulgaris (SIAM J. Comp. 13), and Sommer, Feder and Shalvi (SIAM J. Disc. Math. 09),…

We propose an unsupervised variational model for disentangling video into independent factors, i.e. each factor's future can be predicted from its pa…

Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. The …

In this paper, we developed several novel unbiased estimators for entropy bonus and its gradient. We did experimental work for two environments with large multi-dimensional action spaces. We found that the smoothed estimate of the entropy and the un…

In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces s…

Shells, i.e., objects made of a thin layer of material following a surface, are among the most common structures in use. They are highly efficient, i…

By signing up you accept our content policy

Already have an account? Sign in

No a member yet? Create an account