Lecture

Sparse Communication: Transformations and Applications

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture by the instructor covers the evolution from sparse modeling to sparse communication, focusing on the use of sparse transformations in neural networks for natural language processing tasks. The talk explores various sparse regularization techniques, such as sparse neuron activations and structured sparsity, and their applications in machine-human communication. It delves into the concepts of sparsemax, entmax, and mixed distributions, highlighting their role in bridging the gap between discrete and continuous models. The lecture also discusses the implications of sparse communication for explainability and emergent communication in machine learning.

Official source

Related concepts (32)

Natural language processing

Natural language processing (NLP) is an interdisciplinary subfield of linguistics and computer science. It is primarily concerned with processing natural language datasets, such as text corpora or speech corpora, using either rule-based or probabilistic (i.e. statistical and, most recently, neural network-based) machine learning approaches. The goal is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them.

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Softmax function

The softmax function, also known as softargmax or normalized exponential function, converts a vector of K real numbers into a probability distribution of K possible outcomes. It is a generalization of the logistic function to multiple dimensions, and used in multinomial logistic regression. The softmax function is often used as the last activation function of a neural network to normalize the output of a network to a probability distribution over predicted output classes, based on Luce's choice axiom.

Neural network

A neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.

History of natural language processing

The history of natural language processing describes the advances of natural language processing (Outline of natural language processing). There is some overlap with the history of machine translation, the history of speech recognition, and the history of artificial intelligence. The history of machine translation dates back to the seventeenth century, when philosophers such as Leibniz and Descartes put forward proposals for codes which would relate words between languages.

Related lectures (64)

Sequence to Sequence Models: Overview and Applications

Covers sequence to sequence models, their architecture, applications, and the role of attention mechanisms in improving performance.

Deep Learning for Question Answering

Explores deep learning for question answering, analyzing neural networks and model robustness to noise.

Language Models: Fixed-context and Recurrent Neural Networks

Discusses language models, focusing on fixed-context neural models and recurrent neural networks.

Introduction to Modern Natural Language Processing

Introduces the course on Modern Natural Language Processing, covering its significance, applications, challenges, and advancements in technology.

Transformers: Revolutionizing Attention Mechanisms in NLP