Transformers: Pre-Training

Description

This lecture covers the challenges of the Transformer model, such as quadratic compute in self-attention and the limitations of absolute position representations. It also explores recent advancements in reducing the quadratic self-attention cost and improving position representations using relative linear position attention. Additionally, it discusses the concept of graph-to-graph Transformers and summarizes the key features of Transformers, including bidirectional self-attention and the use of multiple attention heads. The lecture delves into pretraining models like ELMO, BERT, and GPT, and examines word structure and subword models, emphasizing the importance of subword tokenization in NLP.

Official source

https://mediaspace.epfl.ch/media/0_o3xnh2gs

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (1)

Related concepts (23)

Transformer (machine learning model)

A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.

Generative pre-trained transformer

Generative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. The first GPT was introduced in 2018 by OpenAI. GPT models are artificial neural networks that are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.

ChatGPT

ChatGPT, which stands for Chat Generative Pre-trained Transformer, is a large language model-based chatbot developed by OpenAI and launched on November 30, 2022, notable for enabling users to refine and steer a conversation towards a desired length, format, style, level of detail, and language used. Successive prompts and replies, known as prompt engineering, are considered at each conversation stage as a context. ChatGPT is built upon GPT-3.

Large language model

A large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.

Attention

Attention is the concentration of awareness on some phenomenon to the exclusion of other stimuli. It is a process of selectively concentrating on a discrete aspect of information, whether considered subjective or objective. William James (1890) wrote that "Attention is the taking possession by the mind, in clear and vivid form, of one out of what seem several simultaneously possible objects or trains of thought. Focalization, concentration, of consciousness are of its essence.