Flipboard

MARCH 13, 2023

OpenAI has pioneered a technique to shape its models’ behaviors using something called reinforcement learning with human feedback (RLHF). Having a human periodically check on the reinforcement learning system’s output and give feedback allows reinforcement learning systems to learn even when the reward function is hidden. “I’m

Deep Learning 172

Deep Learning Deep Learning Supervised Learning AI 172

Hacker News

MARCH 25, 2022

First described in a 2017 paper from Google, transformers are among the newest and one of the most powerful classes of models invented to date. They’re driving a wave of advances in machine learning some have dubbed transformer AI. Now we see self-attention is a powerful, flexible tool for learning,” he added. “Now

Machine Learning 182

Machine Learning Machine Learning Database AI 182

Explosion

JANUARY 12, 2018

spaCy In 2017 spaCy grew into one of the most popular open-source libraries for Artificial Intelligence. Highlights included: Developed new deep learning models for text classification, parsing, tagging, and NER with near state-of-the-art accuracy. spaCy’s Machine Learning library for NLP in Python. Released Prodigy v1.0,

Machine Learning 52

Machine Learning Machine Learning Supervised Learning Python 52

Explosion

APRIL 1, 2017

Prodigy features many of the ideas and solutions for data collection and supervised learning outlined in this blog post. It’s a cloud-free, downloadable tool and comes with powerful active learning models. Transfer learning and better annotation tooling are both key to our current plans for spaCy and related projects.

Supervised Learning 40

Supervised Learning Machine Learning Machine Learning Algorithm 40

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

Mlearning.ai

JULY 31, 2023

Things become more complex when we apply this information to Deep Learning (DL) models, where each data type presents unique challenges for capturing its inherent characteristics. 2017) paper, vector embeddings have become a standard for training text-based DL models. Likewise, sound and text have no meaning to a computer.

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). His specialty is Natural Language Processing (NLP) and is passionate about deep learning.

ML 98

ML ML Data Scientist AWS 98