Hacker News

MAY 3, 2023

In the grand tapestry of modern artificial intelligence, how do we ensure that the threads we weave when designing powerful AI systems align with the intricate patterns of human values? 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

Snorkel AI

MARCH 1, 2023

Foundation Models (FMs), such as GPT-3 and Stable Diffusion, mark the beginning of a new era in machine learning and artificial intelligence. Foundation models are large AI models trained on enormous quantities of unlabeled data—usually through self-supervised learning. What is self-supervised learning?

Natural Language Processing 83

Natural Language Processing Supervised Learning Machine Learning Machine Learning 83

Applied Data Science

MARCH 11, 2022

In contrast to classification, a supervised learning paradigm, generation is most often done in an unsupervised manner: for example an autoencoder , in the form of a neural network, can capture the statistical properties of a dataset. One does not need to look into the math to see that it’s inherently more difficult.

AI 130

AI AI Data Science Machine Learning 130

Mlearning.ai

JULY 31, 2023

2017) paper, vector embeddings have become a standard for training text-based DL models. Data2Vec: A General Framework For Self-Supervised Learning in Speech, Vision and Language. It is none other than the legendary Vector Embeddings! Without further ado, let’s dive right in! A vector embedding is an object (e.g., and Auli, M.,

Deep Learning 52

Deep Learning Deep Learning Supervised Learning Algorithm 52

AWS Machine Learning Blog

AUGUST 16, 2023

Training machine learning (ML) models to interpret this data, however, is bottlenecked by costly and time-consuming human annotation efforts. One way to overcome this challenge is through self-supervised learning (SSL). The types of land cover in each image, such as pastures or forests, are annotated according to 19 labels.

ML 92

ML ML Data Scientist AWS 92

Google Research AI blog

JANUARY 18, 2023

One of the broad key challenges in artificial intelligence is to build systems that can perform multi-step reasoning, learning to break down complex problems into smaller tasks and combining solutions to those to address the larger problem. Combining this with PixelCNN yielded high-quality images.

ML 132

ML ML AI AI 132

Flipboard

APRIL 4, 2025

Supervised learning can help tune LLMs by using examples demonstrating some desired behaviors, which is called supervised fine-tuning (SFT). 2017) provided the first evidence that RLHF could be economically scaled up to practical applications. 2017) Deep reinforcement learning from human preferences.

AI 147

AI AI Algorithm Artificial Intelligence 147

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. Artificial Intelligence (AI) ersetzt. GPT-3 wurde mit mehr als 100 Milliarden Wörter trainiert, das parametrisierte Machine Learning Modell selbst wiegt 800 GB (quasi nur die Neuronen!)

Big Data 147

Big Data Big Data Apache Hadoop Data Science 147