In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes. We exploit the peculiarities of NCD to build a new framework, named Neighborhood Contrastive Learning (NCL), to learn discriminative representations that are important to clustering performance. Our contribution is twofold. First, we find that a feature extractor trained on the labeled set generates representations in which a generic query sample and its neighbors are likely to share the same class. We exploit this observation to retrieve and aggregate pseudo-positive pairs with contrastive learning, thus encouraging the model to learn more discriminative representations. Second, we notice that most of the instances are easily discriminated by the network, contributing less to the contrastive loss. To overcome this issue, we propose to generate hard negatives by mixing labeled and unlabeled samples in the feature space. We experimentally demonstrate that these two ingredients significantly contribute to clustering performance and lead our model to outperform state-of-the-art methods by a large margin (e.g., clustering accuracy +13% on CIFAR-100 and +8% on ImageNet).

Modeling and simulating a power distribution network (PDN) for printed circuit boards (PCBs) with irregular board shapes and multi-layer stackup is computationally inefficient using full-wave simulations. This paper presents a new concept of using deep learning for PDN impedance prediction. A boundary element method (BEM) is applied to efficiently calculate the impedance for arbitrary board shape and stackup. Then over one million boards with different shapes, stackup, IC location, and decap placement are randomly generated to train a deep neural network (DNN). The trained DNN can predict the impedance accurately for new board configurations that have not been used for training. The consumed time using the trained DNN is only 0.1 seconds, which is over 100 times faster than the BEM method and 5000 times faster than full-wave simulations.

Visual information extraction (VIE) has attracted increasing attention in recent years. The existing methods usually first organized optical character recognition (OCR) results into plain texts and then utilized token-level entity annotations as supervision to train a sequence tagging model. However, it expends great annotation costs and may be exposed to label confusion, and the OCR errors will also significantly affect the final performance. In this paper, we propose a unified weakly-supervised learning framework called TCPN (Tag, Copy or Predict Network), which introduces 1) an efficient encoder to simultaneously model the semantic and layout information in 2D OCR results; 2) a weakly-supervised training strategy that utilizes only key information sequences as supervision; and 3) a flexible and switchable decoder which contains two inference modes: one (Copy or Predict Mode) is to output key information sequences of different categories by copying a token from the input or predicting one in each time step, and the other (Tag Mode) is to directly tag the input sequence in a single forward pass. Our method shows new state-of-the-art performance on several public benchmarks, which fully proves its effectiveness.

To assess the generalizability of a deep learning pneumothorax detection model on datasets from multiple external institutions and examine patient and acquisition factors that might influence performance. In this retrospective study, a deep learning model was trained for pneumothorax detection by merging two large open-source chest radiograph datasets: ChestX-ray14 and CheXpert. It was then tested on six external datasets from multiple independent institutions (labeled A–F) in a retrospective case-control design (data acquired between 2016 and 2019 from institutions A–E; institution F consisted of data from the MIMIC–CXR dataset). Performance on each dataset was evaluated by using area under the receiver operating characteristic curve (AUC) analysis, sensitivity, specificity, and positive and negative predictive values, with two radiologists in consensus being used as the reference standard. Patient and acquisition factors that influenced performance were analyzed.

Artificial intelligence (AI) is taking over just about every aspect of communication. From Siri answering your vocalized questions to Amazon recommending products based on your browsing history, AI has permeated our lives in ways we don't even think about anymore. AI is developing faster than ever -- experts have projected the global AI market value to reach $190 billion by 2025. It's not time to panic about Skynet taking over just yet, but it is important to understand how AI is currently impacting and will continue to impact writers and other professions. Human writers will always have a place in content creation.

PyTorch is an open source deep learning framework built to be flexible and modular for research, with the stability and support needed for production deployment. It enables fast, flexible experimentation through a tape-based autograd system designed for immediate and python-like execution.

A newly re-invigorated form of machine learning, which is itself a subset of artificial intelligence, deep learning employs powerful computers, massive data sets, "supervised" (trained) neural networks and an algorithm called back-propagation (backprop for short) to recognize objects and translate speech in real time by mimicking the layers of neurons in a human brain's neocortex. Deep learning (sometimes known as deep structured learning) is a subset of machine learning, where machines employ artificial neural networks to process information. Inspired by biological nodes in the human body, deep learning helps computers to quickly recognize and process images and speech. Computers then "learn" what these images or sounds represent and build an enormous database of stored knowledge for future tasks. In essence, deep learning enables computers to do what humans do naturally- learn by immersion and example.

Programming competition problems are pervasive in the AI community. They can be used to evaluate programmers' abilities to solve artificial tasks as well as to test the limits of state-of-the-art algorithms. A research team from MIT, Allen Institute for AI and Microsoft Research recently introduced Python Programming Puzzles (P3), a novel and open-source collection of programming challenges that capture the essence of puzzles and can be used to teach and evaluate an AI's programming proficiency. The proposed puzzles take the form of a Python function with the answer as an argument. The goal is to find an input x that makes the output of the function true, i.e., a valid answer x satisfies f(x) True.

In short, machine learning algorithms are able to detect and learn from patterns in data and make their own predictions. In traditional programming, someone writes a series of instructions so that a computer can transform input data into a desired output. Instructions are mostly based on an IF-THEN structure: when certain conditions are met, the program executes a specific action. Machine learning, on the other hand, is an automated process that enables machines to solve problems and take actions based on past observations. Basically, the machine learning process includes these stages: Feed a machine learning algorithm examples of input data and a series of expected tags for that input.

Facebook's new Artificial Intelligence technology not only identifies Deepfakes, it can also gives hints about their origin Artificial intelligence (AI) created videos and pictures have become much popular and that can create some serious problems as well, because you can create fake videos, and manipulated images of any type to put anyone in trouble. Deepfakes use deep learning models to create fictitious photos, videos, and events. These days, deepfakes look so realistic that it becomes very difficult to identify the real picture from the fake one with a normal human eye, therefore, Facebook's AI team has created a model in collaboration with a group of Michigan State University that has the ability to identify not only the fabricated picture or videos, but it can even trace the origin. The latest technology of Facebook checks the resemblances from a compilation of deepfakes datasets to find out if they have a common basis, looking for a distinctive model such as small specks of noise or minor quirks in the color range of a photo. By spotting the small finger impressions in the photo, the new AI model is capable to distinguish particulars of how the impartial network that produced the photo was invented, such as how large the prototype is and how it was prepared.