Publications by profiles

Latest News – Editorial Line – Volunteers – Events – Specialties – Books– Contact – About


General Profile

R0:5e6fade87218b43e4b8d96158080cc85-A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning

A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning

This paper provides a succinct overview of this emerging theory of overparameterized ML (henceforth abbreviated as TOPML) that explains these recent findings through a statistical signal processing perspective. We emphasize the unique aspects that define the TOPML research area as a subfield of modern ML theory and outline interesting open questions that remain.

R0:97532435b0393f0a6ae72973cc68382e-How to avoid machine learning pitfalls: a guide for academic researchers

How to avoid machine learning pitfalls: a guide for academic researchers

This document gives a concise outline of some of the common mistakes that occur when using machine learning techniques, and what can be done to avoid them. It is intended primarily as a guide for research students, and focuses on issues that are of particular concern within academic research, such as the need to do rigorous comparisons and reach valid conclusions. It covers five stages of the machine learning process: what to do before model building, how to reliably build models, how to robustly evaluate models, how to compare models fairly, and how to report results

R0:8477de576deaf0ef41a00ad9e17c7171-Partial Differential Equations is All You Need for Generating Neural Architectures -- A Theory for Physical Artificial Intelligence Systems

Partial Differential Equations is All You Need for Generating Neural Architectures — A Theory for Physical Artificial Intelligence Systems

In this work, we generalize the reaction-diffusion equation in statistical physics, Schrödinger equation in quantum mechanics, Helmholtz equation in paraxial optics into the neural partial differential equations (NPDE), which can be considered as the fundamental equations in the field of artificial intelligence research

Probabilistic Machine Learning: An Introduction

Probabilistic Machine Learning: An Introduction

“In this book, we will cover the most common types of ML, but from a probabilistic perspective. Roughly speaking, this means that we treat all unknown quantities (e.g., predictions about the future value of some quantity of interest, such as tomorrow’s temperature, or the parameters of some model) as random variables, that are endowed with probability distributions which describe a weighted set of possible values the variable may have.[…].”.

R0:5ad410ba3fa0191312506cf94754bfd9-Addressing Ethical Dilemmas in AI: Listening to Engineers

Addressing Ethical Dilemmas in AI: Listening to Engineers

Documentation is key – design decisions in AI development must be documented in detail, potentially taking inspiration from the field of risk management. There is a need to develop a framework for large-scale testing of AI effects, beginning with public tests of AI systems, and moving towards real-time validation and monitoring. Governance frameworks for decisions in AI development need to be clarified, including the questions of post-market surveillance of product or system performance. Certification of AI ethics expertise would be helpful to support professionalism in AI development teams. Distributed responsibility should be a goal, resulting in a clear definition of roles and responsibilities as well as clear incentive structures for taking in to account broader ethical concerns in the development of AI systems. Spaces for discussion of ethics are lacking and very necessary both internally in companies and externally, provided by independent organisations. Looking to policy ensuring whistleblower protection and ombudsman position within companies, as well as participation from professional organisations. One solution is to look to the existing EU RRI framework and to ensure multidisciplinarity in AI system development team composition. The RRI framework can provide systematic processes for engagement with stakeholders and ensuring that problems are better defined. The challenges of AI systems point to a general lack in engineering education. We need to ensure that technical disciplines are empowered to identify ethical problems, which requires broadening technical education programs to include societal concerns. Engineers advocate for public transparency of adherence to standards and ethical principles for AI-driven products and services to enable learning from each other’s mistakes and to foster a no-blame culture.

Yann LeCun’s Deep Learning Course at CDS

Yann LeCun’s Deep Learning Course at CDS

This course concerns the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition. The prerequisites include: DS-GA 1001 Intro to Data Science or a graduate-level machine learning course.

Fourier Neural Operator for Parametric Partial Differential Equations

Fourier Neural Operator for Parametric Partial Differential Equations

The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution.

R0_b6959f4e35b2c24097cf630fa7cea606-Evaluating and Characterizing Human Rationales

Evaluating and Characterizing Human Rationales

Two main approaches for evaluating the quality of machine-generated rationales are: 1) using human rationales as a gold standard; and 2) automated metrics based on how rationales affect model behavior.

The future of AI

If you wonder what is next in the evolution towards general AI then this session is for you. We have seen some painful failures of artificial intelligence pointing to a lack of ‘common sense’. Are neural networks really the solution we seek or is a new path needed? Find out what IBM Research is cooking in terms of hardware and software in the never ending quest towards General AI.

The Deep Learning Revolution and Its Implications for Computer Architecture and Chip Design

The past decade has seen a remarkable series of advances in machine learning, and in particular deep learning approaches based on artificial neural networks, to improve our abilities to build more accurate systems across a broad range of areas, including computer vision, speech recognition, language translation, and natural language understanding tasks.

TechDispatch #1/2020: Contact Tracing with Mobile Applications

In public health, contact tracing is the process to identify individuals who have been in contact with infected persons. Proximity tracing with smartphone applications and sensors could support contact tracing. It involves processing of sensitive personal data.

Cumplimiento normativo y seguridad TI en IoT

La conectividad y el tratamiento masivo de datos son dos pilares esenciales para el desarrollo de estos sistemas, los cuales, a su vez, introducen riesgos de seguridad y privacidad que deben ser tratados adecuadamente.

The European Data Protection Supervisor, 2019 Annual Report a year of transition

With new legislation on data protection in the EU now in place, our greatest challenge moving into 2020 is to ensure that this legislation produces the promised results. This includes ensuring that new rules on ePrivacy remain firmly on the EU agenda. Awareness of the issues surrounding data protection and privacy and the importance of rotecting these fundamental rights is at an all time high and we cannot allow this momentum to decline.

Defining Artificial Intelligence |🇪🇸 Definiendo Inteligencia Artificial

The starting point to develop the operational definition is the definition of AI adopted by the High Level Expert Group on artificial intelligence. To derive this operational definition we have followed a mixed methodology. On one hand, we apply natural language processing methods to a large set of AI literature. On the other hand, we carry out a qualitative analysis on 55 key documents including artificial intelligence definitions from three complementary perspectives: policy, research and industry.

Artificial Intelligence: Foundations of Computational Agents

It presents artificial intelligence as the study of the design of intelligent computational agents. The book is structured as a textbook, but it is accessible to a wide audience of professionals and researchers. In the last decades we have witnessed the emergence of artificial intelligence as a serious science and engineering discipline. This book provides an accessible synthesis of the field aimed at undergraduate and graduate students. It provides a coherent vision of the foundations of the field as it is today. It aims to provide that synthesis as an integrated science, in terms of a multi-dimensional design space that has been partially explored. As with any science worth its salt, artificial intelligence has a coherent, formal theory and a rambunctious experimental wing. The book balances theory and experiment, showing how to link them intimately together. It develops the science of AI together with its engineering applications.

Robots in a rush: time-aware AI aids human-machine interaction

The TIMESTORM consortium, funded by the EU’s Future and Emerging Technologies (FET) programme, has transformed the notion of time perception in artificial intelligence from an immature, poorly defined subject into a promising new research strand, drawing on diverse expertise in psychology and neurosciences as well as robotics and cognitive systems.

Artificial Intelligence in Society

“The artificial intelligence (AI) landscape has evolved significantly from 1950 when Alan Turing first posed the question of whether machines can think. Today, AI is transforming societies and economies. It promises to generate productivity gains, improve well-being and help address global challenges, such as climate change, resource scarcity and health crises. Yet, as AI applications are adopted around the world, their use can raise questions and challenges related to human values, fairness, human determination, privacy, safety and accountability, among others. This report helps build a shared understanding of AI in the present and near-term by mapping the AI technical, economic, use case and policy landscape and identifying major public policy considerations. It is also intended to help co-ordination and consistency with discussions in other national and international fora”. (OECD)

La era de los datos | 🇬🇧 The Age of Data

La era de los datos | 🇬🇧 The Age of Data
“Diecinueve grandes expertos de todo el mundo esbozan las reformas ambiciosas y radicales necesarias para encarar los desafíos de la era de los datos”. | 🇬🇧 “Nineteen leading experts from all over the world outline the major, radical reforms needed to address the challenges of the Age of Data”. (OpenMind. BBVA).


Something went wrong. Please refresh the page and/or try again.

Share this on: