Publications

We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations.

We performed an experiment to test learning in neural nets.

Multihop self-backhauling is a key enabling technology for millimeter wave cellular deployments.

Nonlinear energy harvesters (EH) behave differently depending on the range of their input power.

Viola and Jones (VJ) cascade classification methods have proven to be very successful in detecting objects belonging to a single class - e.g., faces.

Given the exponential increase in broadband cellular traffic it is imperative that scalable traffic measurement and monitoring techniques be developed to aid various resource management methods.

Using monitored physical parameters in a learning process, we decrease design margins by reducing uncertainties on the input parameters of a Quality of Transmission (QoT) tool, improving the accura

The learning data requirements are analyzed for the construction of stealth attacks in state estimation.

Recent negative results on learning Deterministic Finite Automata (DFAs) have encouraged researchers to investigate alternative models of learning in which more information is available to the lear

We construct a graph neural network (GNN) to compute, within a time budget of 1 to 2 milliseconds required by practical systems, the optimal linear precoder (OLP) maximizing the minimal (Max-Min) d