Related papers: Capacity of Remote Classification Over Wireless Ch…

A fundamental problem in adversarial machine learning is to quantify how much training data is needed in the presence of evasion attacks. In this paper we address this issue within the framework of PAC learning, focusing on the class of…

In this paper, we consider a remote inference system, where a neural network is used to infer a time-varying target (e.g., robot movement), based on features (e.g., video clips) that are progressively received from a sensing node (e.g., a…

The intrinsic complexity of nonlinear optical phenomena offers a fundamentally new resource to analog brain-inspired computing, with the potential to address the pressing energy requirements of artificial intelligence. We introduce and…

Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge. This paper presents an energy-efficient edge processing…

With the ever-increasing range of applications of Internet in Things (IoT) and sensor networks, challenges are emerging in various categories of classification tasks. Applications such as vehicular networking, UAV swarm coordination and…

This paper develops upper bounds on the end-to-end transmission capacity of multi-hop wireless networks. Potential source-destination paths are dynamically selected from a pool of randomly located relays, from which a closed-form lower…

In this paper, we present a new technique to obtain upper bounds on undirected unicast network information capacity. Using this technique, we characterize an upper bound, called partition bound, on the symmetric rate of information flow in…

We develop a novel framework for proving converse theorems for channel coding, which is based on the analysis technique of multicast transmission with an additional auxiliary receiver, which serves as a genie to the original receiver. The…

We formally define algorithmic capture of combinatorial tasks as the ability of a transformer to extrapolate to arbitrary task sizes with controllable error and logarithmic sample adaptation, providing a sharp scaling criterion for…

Optical wireless communication (OWC) using intensity-modulation and direct-detection (IM/DD) has a channel model which possesses unique features, due to the constraints imposed on the channel input. The aim of this tutorial is to overview…

The one-class classification problem is a well-known research endeavor in pattern recognition. The problem is also known under different names, such as outlier and novelty/anomaly detection. The core of the problem consists in modeling and…

In wireless sensor networks, various applications involve learning one or multiple functions of the measurements observed by sensors, rather than the measurements themselves. This paper focuses on type-threshold functions, e.g., the maximum…

Cellular data traffic almost doubles every year, greatly straining network capacity. The main driver for this development is wireless video. Traditional methods for capacity increase (like using more spectrum and increasing base station…

Wireless sensor networks are composed of distributed sensors that can be used for signal detection or classification. The likelihood functions of the hypotheses are often not known in advance, and decision rules have to be learned via…

This tutorial-style overview article examines the fundamental principles and methods of robustness, using wireless sensing and communication (WSC) as the narrative and exemplifying framework. First, we formalize the conceptual and…

The growing popularity of big data and Internet of Things (IoT) applications bring new challenges to the wireless communication community. Wireless transmission systems should more efficiently support the large amount of data traffics from…

One of the most common problems preventing the application of prediction models in the real world is lack of generalization: The accuracy of models, measured in the benchmark does repeat itself on future data, e.g. in the settings of real…

Wireless network capacity is one of the most important performance metrics for wireless communication networks. Future wireless networks will be composed of extremely large number of base stations (BSs) and users, and organized in the form…

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…