Lecture

Neural Networks: Multilayer Perceptrons

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 introduces Multilayer Perceptrons (MLP) as a flexible function family that can solve complex problems by finding smart features and regression coefficients simultaneously. It covers the concept of artificial neurons, popular activation functions like relu and sigmoid, matrix notation for MLP, and the importance of flexibility and regularization in neural networks. The lecture also discusses regression and classification tasks with MLPs, showcasing the XOR problem and the parametrization of conditional densities. Practical examples include regression with MLPs and classification with MLPs for tasks like fitting weather data and predicting analyte retention time in liquid chromatography.

Official source

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Statistics

Data analysis: Regression analysis

Related concepts (32)

Artificial neural network

Artificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.

Perceptrons (book)

Perceptrons: an introduction to computational geometry is a book written by Marvin Minsky and Seymour Papert and published in 1969. An edition with handwritten corrections and additions was released in the early 1970s. An expanded edition was further published in 1987, containing a chapter dedicated to counter the criticisms made of it in the 1980s. The main subject of the book is the perceptron, a type of artificial neural network developed in the late 1950s and early 1960s.

High-performance liquid chromatography

High-performance liquid chromatography (HPLC), formerly referred to as high-pressure liquid chromatography, is a technique in analytical chemistry used to separate, identify, and quantify each component in a mixture. It relies on pumps to pass a pressurized liquid solvent containing the sample mixture through a column filled with a solid adsorbent material. Each component in the sample interacts slightly differently with the adsorbent material, causing different flow rates for the different components and leading to the separation of the components as they flow out of the column.

Chromatography

In chemical analysis, chromatography is a laboratory technique for the separation of a mixture into its components. The mixture is dissolved in a fluid solvent (gas or liquid) called the mobile phase, which carries it through a system (a column, a capillary tube, a plate, or a sheet) on which a material called the stationary phase is fixed. Because the different constituents of the mixture tend to have different affinities for the stationary phase and are retained for different lengths of time depending on their interactions with its surface sites, the constituents travel at different apparent velocities in the mobile fluid, causing them to separate.

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

Related lectures (57)

The Hidden Convex Optimization Landscape of Deep Neural Networks

Explores the hidden convex optimization landscape of deep neural networks, showcasing the transition from non-convex to convex models.

Deep Learning: Multilayer Perceptron and Training

Covers deep learning fundamentals, focusing on multilayer perceptrons and their training processes.

Nonlinear Machine Learning: k-Nearest Neighbors and Feature Expansion

Covers the transition from linear to nonlinear models, focusing on k-NN and feature expansion techniques.

Neural Networks: Training and Activation

Explores neural networks, activation functions, backpropagation, and PyTorch implementation.

Landscape and Generalisation in Deep Learning