Lecture

Neural Networks Recap: Activation Functions

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.

In course

DH-406: Machine learning for DH

This course aims to introduce the basic principles of machine learning in the context of the digital humanities. We will cover both supervised and unsupervised learning techniques, and study and implement methods to analyze diverse data types, such as imag ...

Description

This lecture provides a recap on artificial neural networks, focusing on activation functions for hidden layers and the final output layer. It covers the basics of training a multilayer perceptron, working with images, and the concept of convolutional layers in Convolutional Neural Networks (CNN). The instructor explains the importance of regularization techniques to prevent overfitting and discusses the transition from supervised learning to data transformation for further analysis, including dimensionality reduction methods like PCA and Fisher Linear Discriminant Analysis. The lecture concludes with a brief overview of t-distributed stochastic neighbor embedding (t-SNE) for data visualization.

Instructor

Mathieu Salzmann

I am a Senior Researcher at EPFL-CVLab, and, since May 2020, an Artificial Intelligence Engineer at ClearSpace (50%). Previously, I was a Senior Researcher and Research Leader in NICTA's computer vision research group. Prior to this, from Sept. 2010 to Jan 2012, I was a Research Assistant Professor at TTI-Chicago, and, from Feb. 2009 to Aug. 2010, a postdoctoral fellow at ICSI and EECS at UC Berkeley under the supervision of Prof. Trevor Darrell. I obtained my PhD in Jan. 2009 from EPFL under the supervision of Prof. Pascal Fua.

Official source

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Related concepts (32)

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.

Dimensionality reduction

Dimensionality reduction, or dimension reduction, is the transformation of data from a high-dimensional space into a low-dimensional space so that the low-dimensional representation retains some meaningful properties of the original data, ideally close to its intrinsic dimension. Working in high-dimensional spaces can be undesirable for many reasons; raw data are often sparse as a consequence of the curse of dimensionality, and analyzing the data is usually computationally intractable (hard to control or deal with).

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.

Data analysis

Data analysis is the process of inspecting, cleansing, transforming, and modeling data with the goal of discovering useful information, informing conclusions, and supporting decision-making. Data analysis has multiple facets and approaches, encompassing diverse techniques under a variety of names, and is used in different business, science, and social science domains. In today's business world, data analysis plays a role in making decisions more scientific and helping businesses operate more effectively.

Types of artificial neural networks

There are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.

Related lectures (64)

Clustering & Density Estimation

Covers clustering, PCA, LDA, K-means, GMM, KDE, and Mean Shift algorithms for density estimation and clustering.

Dimensionality Reduction

Introduces artificial neural networks and explores various dimensionality reduction techniques like PCA, LDA, Kernel PCA, and t-SNE.

Neural Networks: Multilayer Perceptrons

Covers Multilayer Perceptrons, artificial neurons, activation functions, matrix notation, flexibility, regularization, regression, and classification tasks.

Dimensionality Reduction: PCA & LDA

Covers PCA and LDA for dimensionality reduction, explaining variance maximization, eigenvector problems, and the benefits of Kernel PCA for nonlinear data.

Landscape and Generalisation in Deep Learning