NYU Center for Data Science

SEPTEMBER 13, 2024

The world of multi-view self-supervised learning (SSL) can be loosely grouped into four families of methods: contrastive learning, clustering, distillation/momentum, and redundancy reduction.

Supervised Learning 62

Supervised Learning Clustering Machine Learning Machine Learning 62

Google Research AI blog

JULY 18, 2023

Alternatively, self-supervised learning (SSL) methods (e.g., SimCLR and MoCo v2 ), which leverage a large amount of unlabeled data to learn representations that capture periodic or quasi-periodic temporal dynamics, have demonstrated success in solving classification tasks. video or satellite imagery).

Supervised Learning 70

Supervised Learning Machine Learning Machine Learning 70

Google Research AI blog

APRIL 30, 2023

Posted by Catherine Armato, Program Manager, Google The Eleventh International Conference on Learning Representations (ICLR 2023) is being held this week as a hybrid event in Kigali, Rwanda. We are proud to be a Diamond Sponsor of ICLR 2023, a premier conference on deep learning, where Google researchers contribute at all levels.

Supervised Learning 105

Supervised Learning Machine Learning Machine Learning Deep Learning 105

Towards AI

AUGUST 29, 2023

Last Updated on August 30, 2023 by Editorial Team Author(s): Tan Pengshi Alvin Originally published on Towards AI. Introducing the backbone of Reinforcement Learning — The Markov Decision Process This member-only story is on us. Let’s first start with a broad overview of Machine Learning. Upgrade to access all of Medium.

Supervised Learning 105

Supervised Learning Machine Learning Machine Learning AI 105

Google Research AI blog

JUNE 18, 2023

Posted by Shaina Mehta, Program Manager, Google This week marks the beginning of the premier annual Computer Vision and Pattern Recognition conference (CVPR 2023), held in-person in Vancouver, BC (with additional virtual content).

Supervised Learning 116

Supervised Learning Deep Learning Deep Learning Artificial Intelligence 116

NYU Center for Data Science

JANUARY 25, 2024

2023’s event, held in New Orleans in December, was no exception, showcasing groundbreaking research from around the globe. In the world of data science, few events garner as much attention and excitement as the annual Neural Information Processing Systems (NeurIPS) conference.

Computer Science 73

Computer Science Computer Science Data Science Supervised Learning 73

ODSC - Open Data Science

AUGUST 29, 2023

Now if you want to take your prompt engineering skills to the next level, or want to learn the basics, then you don’t want to miss ODSC West 2023. At ODSC West, you’ll experience multiple tracks with Large Language Models, having its own track.

Natural Language Processing 98

Natural Language Processing Machine Learning Machine Learning Data Scientist 98

Snorkel AI

MARCH 30, 2023

Here’s an overview of the Data-centric Foundation Model Development capabilities: Warm Start: Auto-label training data using the power of FMs + state-of-the-art zero- or few-shot learning techniques during onboarding, helping get to a powerful baseline “first pass” with minimal human effort. Interested in learning more about Snorkel Flow?

ML 98

ML ML Supervised Learning Azure 98

Dataversity

DECEMBER 16, 2022

2022 was a big year for AI, and we’ve seen significant advancements in various areas – including natural language processing (NLP), machine learning (ML), and deep learning. Unsupervised and self-supervised learning are making ML more accessible by lowering the training data requirements.

Natural Language Processing 52

Natural Language Processing Supervised Learning Deep Learning Deep Learning 52

Snorkel AI

OCTOBER 31, 2023

The Snorkel AI team will present 18 research papers and talks at the 2023 Neural Information Processing Systems (NeurIPS) conference from December 10-16. The Snorkel papers cover a broad range of topics including fairness, semi-supervised learning, large language models (LLMs), and domain-specific models.

Supervised Learning 59

Supervised Learning AI AI Machine Learning 59

Towards AI

MARCH 4, 2023

Last Updated on March 4, 2023 by Editorial Team Author(s): Harshit Sharma Originally published on Towards AI. Fully-Supervised Learning (Non-Neural Network) — powered by — Feature Engineering Supervised learning required input-output examples to train the model. Let’s get started !!

Supervised Learning 98

Supervised Learning AI AI ML 98

Google Research AI blog

JULY 23, 2023

Google is proud to be a Diamond Sponsor of the 40th International Conference on Machine Learning (ICML 2023), a premier annual conference, which is being held this week in Honolulu, Hawaii. Google is also proud to be a Platinum Sponsor for both the LatinX in AI and Women in Machine Learning workshops. Registered for ICML 2023?

Machine Learning 77

Machine Learning Machine Learning ML ML 77

BAIR

JULY 10, 2023

Figure 1: stepwise behavior in self-supervised learning. When training common SSL algorithms, we find that the loss descends in a stepwise fashion (top left) and the learned embeddings iteratively increase in dimensionality (bottom left). and “how does that learning actually occur?” lack basic answers.

Supervised Learning 40

Supervised Learning Deep Learning Deep Learning Algorithm 40

NYU Center for Data Science

NOVEMBER 15, 2023

We’re excited to announce that many CDS faculty, researchers, and students will present at the upcoming thirty-seventh 2023 NeurIPS (Neural Information Processing Systems) Conference , taking place Sunday, December 10 through Saturday, December 16. The conference will take place in-person at the New Orleans Ernest N.

Data Science 81

Data Science Computer Science Computer Science Supervised Learning 81

Towards AI

JULY 22, 2023

Last Updated on July 24, 2023 by Editorial Team Author(s): Cristian Originally published on Towards AI. In the context of Machine Learning, data can be anything from images, text, numbers, to anything else that the computer can process and learn from. Instead, it learns by finding patterns and structures in the input data.

ML 98

ML ML Supervised Learning Machine Learning 98

Google Research AI blog

MAY 25, 2023

Chirp is able to cover such a wide variety of languages by leveraging self-supervised learning on unlabeled multilingual dataset with fine-tuning on a smaller set of labeled data. Chirp is now available in the Google Cloud Speech-to-Text API , allowing users to perform inference on the model through a simple interface.

Deep Learning 90

Deep Learning Deep Learning AI AI 90

Snorkel AI

OCTOBER 31, 2023

The Snorkel AI team will present 18 research papers and talks at the 2023 Neural Information Processing Systems (NeurIPS) conference from December 10-16. The Snorkel papers cover a broad range of topics including fairness, semi-supervised learning, large language models (LLMs), and domain-specific models.

Supervised Learning 52

Supervised Learning AI AI Machine Learning 52

AWS Machine Learning Blog

SEPTEMBER 10, 2024

The final phase improved on the results of HEEC and PORPOISE—both of which have been trained in a supervised fashion—using a foundation model trained in a self-supervised manner, namely Hierarchical Image Pyramid Transformer (HIPT) ( Chen et al., 2023 ), has been investigated in the final stage of the PoC exercises.

Supervised Learning 95

Supervised Learning Machine Learning Machine Learning AWS 95

Towards AI

APRIL 18, 2023

Last Updated on April 21, 2023 by Editorial Team Author(s): Sriram Parthasarathy Originally published on Towards AI. Building disruptive Computer Vision applications with No Fine-Tuning Imagine a world where computer vision models could learn from any set of images without relying on labels or fine-tuning. Sounds futuristic, right?

Supervised Learning 98

Supervised Learning AI AI Clustering 98

DrivenData Labs

JUNE 14, 2023

Between December 2022 and April 2023, 404 participants from 59 countries signed up to solve the problems posed by the two tracks, and 82 went on to submit solutions. Self-supervised learning allows for effective use of unlabeled data for training models for representation learning tasks.

Supervised Learning 174

Supervised Learning Artificial Intelligence Artificial Intelligence AI 174

Becoming Human

MAY 15, 2023

The two most common types of supervised learning are classification , where the algorithm predicts a categorical label, and regression , where the algorithm predicts a numerical value.

Data Science 75

Data Science Machine Learning Machine Learning Database 75

Towards AI

JULY 23, 2023

Last Updated on July 25, 2023 by Editorial Team Author(s): Abhijit Roy Originally published on Towards AI. Semi-Supervised Sequence Learning As we all know, supervised learning has a drawback, as it requires a huge labeled dataset to train. But, the question is, how did all these concepts come together?

Natural Language Processing 98

Natural Language Processing Supervised Learning Deep Learning Deep Learning 98

Snorkel AI

SEPTEMBER 29, 2023

Some machine learning algorithms, such as clustering and self-supervised learning , do not require data labels, but their direct business applications are limited. Use cases for supervised machine learning models, on the other hand, cover many business needs.

Machine Learning 59

Machine Learning Machine Learning Data Science ML 59

Towards AI

SEPTEMBER 7, 2023

Last Updated on September 8, 2023 by Editorial Team Author(s): Louis Bouchard Originally published on Towards AI. An analogy to explain how deep learning works… This member-only story is on us. link] When we talk about artificial intelligence, or AI, we tend to mean deep learning. Upgrade to access all of Medium.

Deep Learning 128

Deep Learning Deep Learning AI AI 128

Data Science Dojo

JULY 31, 2024

Training Methodologies Contrastive Learning It is a type of self-supervised learning technique where the model learns to distinguish between similar and dissimilar data points by maximizing the similarity between positive pairs (e.g., BLIP-2 BLIP-2 BLIP-2 was released in early 2023.

AI 367

AI AI Supervised Learning Analytics 367

AssemblyAI

SEPTEMBER 18, 2023

Below, we'll give you the basic know-how you need to understand LLMs, how they work, and the best models in 2023. A large language model (often abbreviated as LLM) is a machine-learning model designed to understand, generate, and interact with human language. Here are the top large language models and frameworks as of 2023.

Deep Learning 52

Deep Learning Deep Learning Natural Language Processing Machine Learning 52

Data Science Blog

MARCH 14, 2023

Von Data Science spricht auf Konferenzen heute kaum noch jemand und wurde hype-technisch komplett durch Machine Learning bzw. AI wiederum scheint spätestens mit ChatGPT 2022/2023 eine neue Euphorie-Phase erreicht zu haben, mit noch ungewissem Ausgang. Neben Supervised Learning kam auch Reinforcement Learning zum Einsatz.

Big Data 147

Big Data Big Data Apache Hadoop Data Science 147

Hacker News

MAY 3, 2023

The core process is a general technique known as self-supervised learning , a learning paradigm that leverages the inherent structure of the data itself to generate labels for training. Fine-tuning may involve further training the pre-trained model on a smaller, task-specific labeled dataset, using supervised learning.

Supervised Learning 181

Supervised Learning Natural Language Processing AI AI 181

ODSC - Open Data Science

MARCH 22, 2023

Learn more about the data-centric AI techniques that power Cleanlab at our upcoming talk at ODSC East 2023. About the author/ODSC East 2023 speaker: Jonas Mueller is Chief Scientist and Co-Founder at Cleanlab, a company providing data-centric AI software to improve ML datasets.

ML 88

ML ML AI AI 88

Data Science Dojo

JULY 2, 2024

Adaptive AI has risen as a transformational technological concept over the years, leading Gartner to name it as a top strategic tech trend for 2023. Machine Learning Algorithms : These algorithms allow AI systems to learn from data and make predictions or decisions based on their learning.

AI 195

AI AI Algorithm Machine Learning 195

Snorkel AI

MARCH 1, 2023

Foundation models are large AI models trained on enormous quantities of unlabeled data—usually through self-supervised learning. What is self-supervised learning? Self-supervised learning is a kind of machine learning that creates labels directly from the input data. Find out in the guide below.

Natural Language Processing 83

Natural Language Processing Supervised Learning Machine Learning Machine Learning 83

Towards AI

JULY 22, 2023

Last Updated on July 24, 2023 by Editorial Team Author(s): Muhammad Arham Originally published on Towards AI. Image by Author Introduction Logistic Regression is a fundamental binary classification algorithm that can learn a decision boundary between two different sets of data attributes.

Algorithm 98

Algorithm Supervised Learning Python AI 98

ODSC - Open Data Science

OCTOBER 3, 2023

The best place to do this is at ODSC West 2023 this October 30th to November 2nd. To excel in this field, you need a diverse skill set that can include a profound understanding of AI models, linguistic expertise, creative problem-solving skills, data analysis capabilities, and strong communication and collaboration skills.

Data Science 97

Data Science Data Analysis Data Analysis Supervised Learning 97

Google Research AI blog

MAY 12, 2023

In “ F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models ”, presented at ICLR 2023 , we introduce a simple and scalable open-vocabulary detection approach built upon frozen VLMs. This is done without a need for knowledge distillation, detection-tailored pre-training, or weakly supervised learning.

Supervised Learning 96

Supervised Learning 96

Snorkel AI

AUGUST 31, 2023

The learning stage uses techniques like semi-supervised learning that use few or no labels. Data + GenAI: a transformative pair Garter's 2023 Hype Cycle for Artificial Intelligence positions generative AI as an enterprise game-changer. Get your copy of the Gartner® Hype Cycle for Artificial Intelligence 2023 report today.

Data Scientist 59

Data Scientist Artificial Intelligence Artificial Intelligence Supervised Learning 59

AWS Machine Learning Blog

MARCH 6, 2024

Nature Reviews Drug Discovery 22, 260–260 (2023). Similarly, pLMs are pre-trained on large protein sequence databases using unlabeled, self-supervised learning. For example, in 2023, a research team described training a 100 billion-parameter pLM on 768 A100 GPUs for 164 days! COVID-19 Spikevax Moderna $21.8

AWS 129

AWS Machine Learning Machine Learning ML 129

Towards AI

MARCH 1, 2023

Last Updated on March 4, 2023 by Editorial Team Author(s): Towards AI Editorial Team Originally published on Towards AI. The class covers algorithms for finding and fixing common issues in ML data, as well as constructing better datasets, with a concentration on data used in supervised learning tasks such as classification.

AI 98

AI AI Machine Learning Machine Learning 98