AI/ML

The correct use of model evaluation, model selection, and algorithm selection techniques is vital in academic machine learning research as well as in many...

We introduce a training objective for continuous normalizing flows that can be used in the absence of samples but in the presence of an energy function. Our...

We propose data thinning, a new approach for splitting an observation into two or more independent parts that sum to the original observation, and that...

Learning from raw high dimensional data via interaction with a given environment has been effectively achieved through the utilization of deep neural...

Classical wisdom suggests that estimators should avoid fitting noise to achieve good generalization. In contrast, modern overparameterized models can yield...

Data-driven approaches coupled with physical knowledge are powerful techniques to model systems. The goal of such models is to efficiently solve for the...

This paper explores connections between margin-based loss functions and consistency in binary classification and regression applications. It is shown that a...

Recently, there has been great interest in connections between continuous-time dynamical systems and optimization methods, notably in the context of...

Federated Learning (FL) refers to learning a high quality global model based on decentralized data storage, without ever copying the raw data. A natural...

Research in human-centered AI has shown the benefits of systems that can explain their predictions. Methods that allow an AI to take advice from humans in...

We present a method to obtain the average and the typical value of the number of critical points of the empirical risk landscape for generalized linear...

We consider the sample complexity of learning with adversarial robustness. Most prior theoretical results for this problem have considered a setting where...

Large pre-trained generative models are known to occasionally output undesirable samples, which undermines their trustworthiness. The common way to mitigate...

Obtaining accurate ground and low-lying excited states of electronic systems is crucial in a multitude of important applications. One ab initio method for...

Bayesian inference for high-dimensional inverse problems is computationally costly and requires selecting a suitable prior distribution. Amortized...

Contrastive Learning has recently achieved state-of-the-art performance in a wide range of tasks. Many contrastive learning approaches use mined hard...

Federated learning refers to the task of machine learning based on decentralized data from multiple clients with secured data privacy. Recent studies show...

We present a novel scheme to boost detection power for kernel maximum mean discrepancy based sequential change-point detection procedures. Our proposed...

In this article we prove that estimator stability is enough to show that leave-one-out cross validation is a sound procedure, by providing concentration...

We present generalized balancing weights, Neural Balancing Weights (NBW), to estimate the causal effects for an arbitrary mixture of discrete and continuous...

Partial differential equations (PDEs) are widely used for description of physical and engineering phenomena. Some key parameters involved in PDEs, which...

Partial differential equations (PDEs) are important tools to model physical systems, and including them into machine learning models is an important way of...

Get a brief introduction into the thinking behind the rise of neural hashing technology — and learn why this may well end up being an enormous shift in AI...

Ambient computing explained - what it is and where it is going next.

US defense officials say their forces around the world would soon use a new technology based on artificial intelligence in face of rapidly evolving drone...

Genesis has suffered steep losses from loans it extended to failed crypto firms Alameda Research and Three Arrows Capital.

Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases. To facilitate the...

Visual Question Answering (VQA) and Image Captioning (CAP), which are among the most popular vision-language tasks, have analogous scene-text versions that...

The EV charging stations are not only growing in size but also going wireless. With IoT connectivity, EV charging becomes more intelligent, convenient, and...

Subbarao Kambhampati, Professor Arizona State University Abstract Despite the surprising power of many modern AI systems that often learn their own...

Contracts are a ubiquitous legal artifact. When we purchase health insurance, move homes, accept a Terms of Service agreement, or start a new job, we sign...

A Large number of ou.

This may be the year when artificial intelligence transforms daily life. So said Brad Smith, president and vice chairman of Microsoft, at a Vatican-organised...

The university had been under attack for pressuring students in crisis to withdraw instead of providing ways to help them to remain on campus.

This is the official website of the AI for Agent-Based Modelling (AI4ABM) Community hosted by Prof. Jakob Foerster, Prof. Ani Calinescu, and Dr Christian...

Investigators found that conditions in three of the company’s facilities risk “serious physical harm” to workers.

Organoid models have revolutionized cancer research through their ability to capture the cellular heterogeneity and spatial organization of a tumor in 3D...

It's the end of the year, and so it's time for KDnuggets to assemble a team of experts and get to the bottom of what the most important data science, machine...

Ten of 15 Spark 01 startups have gone on to raise their seed and Series A while one has recently been acquired, totaling USD 51mn of capital post Spark....

CTO interviews part 2: Brandon Collings The importance of moving to parallel channels will on...

An emotional Jacinda Ardern says she no longer has "enough in the tank" after nearly six years as leader.

Search is possibly one of the main technological advances of the Internet era that did not change much over the past 20 years. Now, we are in for another...

Emergent Ventures is a program from the Mercatus Center at George Mason University run by Tyler Cowen, who is a professor of economics at GMU and an author...

Here's what Ardern said.

ANYONE who’s had Covid is at risk of develop several fatal heart conditions, research suggests. Millions have already had the bug and the majority of Brits...

An emergency helpline and online resource is now available to researchers in the Netherlands.

The feasibility of large-scale testing with lateral flow tests has been demonstrated in the COVID-19 pandemic. This Review examines lessons learned from the...

Info.