We introduce a novel approach to recommendation based on item clustering using non-negative matrix factorization (NMF) techniques. We propose a new algorithm, OCB (Overlapping Clustering Bandits), that groups items into ...

Reinforcement learning is a powerful mechanism for training artificial and real-world agents to perform tasks. Typically, one can define a task for an agent by simply specifying rewards that reflect the agent’s performance. ...

Single-view 3D reconstruction is a task in which an algorithm constructs a 3D model from a single image of an object without seeing the back side of that object or viewing any explicit depth information. We create a ...

We study the problem of building and traversing a search tree for combinatorial optimization problems, which are generally exponential in time complexity and often characterize NP-Hard problems. A typical approach for such ...

The ability to extract sequences of game events for high-resolution e-sport games has traditionally required access to the game’s engine. This difficulty serves as a barrier to groups who don’t possess this access. It is ...

Instabilities in the regulatory mechanisms utilized by the superoxide dismutase 1 glycine 93 to alanine (SOD1 G93A) transgenic mouse to compensate for changes to the system have been postulated to play a considerable role ...

Most deaf children born to hearing parents do not have continuous access to language, leading to weaker short-term memory compared to deaf children born to deaf parents. This lack of short-term memory has serious consequences ...

The Assembly Calculus is a novel framework intended to bridge the gap between the level of neuron and synapses, and that of cognition. The Assembly Calculus is a computational system entailing a basic data item called an ...

TABLA is an innovative framework that accelerates statistical machine learning algorithms. Given the programmer’s code, TABLA generates a hardware accelerator, in the form of synthesizable Verilog code. It contains a set ...

Policy Shaping is an algorithm that takes inputs as state-action-evaluation triples, that the learner obtains through interaction with a teacher. These triples are then used in combination with self exploration and a ...