Related papers: Largenet2: an object-oriented programming library …

We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are based on a solid theoretical analysis, including…

Modern software development is increasingly dependent on components, libraries and frameworks coming from third-party vendors or open-source suppliers and made available through a number of platforms (or forges). This way of writing…

This paper presents the SPARE C++ library, an open source software tool conceived to build pattern recognition and soft computing systems. The library follows the requirement of the generality: most of the implemented algorithms are able to…

A efficient incremental learning algorithm for classification tasks, called NetLines, well adapted for both binary and real-valued input patterns is presented. It generates small compact feedforward neural networks with one hidden layer of…

CB2 is a multi-agent platform to study collaborative natural language interaction in a grounded task-oriented scenario. It includes a 3D game environment, a backend server designed to serve trained models to human agents, and various tools…

The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data processing can be enabled by deploying pretrained models, the…

Discrete event simulators, such as OMNeT++, provide fast and convenient methods for the assessment of algorithms and protocols, especially in the context of wired and wireless networks. Usually, simulation parameters such as topology and…

deal.II is a state-of-the-art finite element library focused on generality, dimension-independent programming, parallelism, and extensibility. Herein, we outline its primary design considerations and its sophisticated features such as…

Neural Networks (NN) provide a solid and reliable way of executing different types of applications, ranging from speech recognition to medical diagnosis, speeding up onerous and long workloads. The challenges involved in their…

Deep learning approaches, known for their ability to model complex relationships and fast execution, are increasingly being applied to solve large optimization problems. However, existing methods often face challenges in simultaneously…

Standard Convolutional Neural Network (CNN) designs rarely focus on the importance of explicitly capturing diverse features to enhance the network's performance. Instead, most existing methods follow an indirect approach of increasing or…

Robot learning has emerged as a promising tool for taming the complexity and diversity of the real world. Methods based on high-capacity models, such as deep networks, hold the promise of providing effective generalization to a wide range…

Stream processing applications have been widely adopted due to real-time data analytics demands, e.g., fraud detection, video analytics, IoT applications. Unfortunately, prototyping and testing these applications is still a cumbersome…

Large Language Models (LLMs) typically generate outputs token by token using a fixed compute budget, leading to inefficient resource utilization. To address this shortcoming, recent advancements in mixture of expert (MoE) models,…

Deep Learning (DL) models are widely used in machine learning due to their performance and ability to deal with large datasets while producing high accuracy and performance metrics. The size of such datasets and the complexity of DL models…

fmeval is an open source library to evaluate large language models (LLMs) in a range of tasks. It helps practitioners evaluate their model for task performance and along multiple responsible AI dimensions. This paper presents the library…

We describe BayesMix, a C++ library for MCMC posterior simulation for general Bayesian mixture models. The goal of BayesMix is to provide a self-contained ecosystem to perform inference for mixture models to computer scientists,…

The challenges involved in executing neural networks (NNs) at the edge include providing diversity, flexibility, and sustainability. That implies, for instance, supporting evolving applications and algorithms energy-efficiently. Using…

We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e.g., meso-skeletons and surfaces, partial and complete scans, etc. The…

The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous…