Search By Subject

We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, ...

The past 3 years of work in NLP have been characterized by the development and deployment of ever larger language models, especially for English. BERT, its variants, GPT-2/3, and others, most recently Switch-C, have pushed the boundaries of the possible ...

This volume, which is also available from http://www.machinelearning.org, the home page of the International Machine Learning Society, contains the technical papers accepted for presentation at ICML-2006, the 23rd International Conference on Machine ...

Tree boosting is a highly effective and widely used machine learning method. In this paper, we describe a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many ...

Unite neuroscience, supercomputing, and nanotechnology to discover, demonstrate, and deliver the brain's core algorithms.

Welcome to the 49th Annual Meeting of the Association for Computational Linguistics in Portland, Oregon. ACL is perhaps the longest-running conference series in computer science. Amazingly, it is still growing. We expect this year's ACL to attract an ...

Finding a lasting solution to the leap seconds problem has become increasingly urgent.

NordiCHI is an international conference and the main Nordic forum for human-computer interaction research. It is the meeting place for researchers from academia as well as industry, designers, practitioners, educators and others from a broad range of ...

Supervised machine-learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world?

Neural net advances improve computers' language ability in many fields.

As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially during the past several years. At least two reasons account for this trend: the first is the wide ...

The kind of causal inference seen in natural human thought can be "algorithmitized" to help produce human-level machine intelligence.

On the matter of memory, there is no comparision. Neural networks are potentially faster and more accurate than humans.

Neural-based multi-task learning has been successfully used in many real-world large-scale applications such as recommendation systems. For example, in movie recommendations, beyond providing users movies which they tend to purchase and watch, the ...

Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a collection of training examples and learn the probability distribution that ...