Lecture

Machine Learning for Feature Extraction

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

MICRO-452: Basics of mobile robotics

This course gives an overview of the field of mobile robotics, introducing to the main techniques and allowing to test them in exercises and a team-based project. ...

Description

This lecture covers the basics of mobile robotics, focusing on vision. It delves into machine learning for feature extraction, 3D vision, linear discriminant, and the optimization of discriminant lines. The instructor explains the discriminant line's slope, feature extraction algorithms, and the use of neural networks for robotics. The lecture also explores the application of deep learning, convolutional neural networks, and the reconstruction of 3D environments using stereo vision and depth cameras.

Instructor

Francesco Mondada

Dr. Mondada received his M.Sc. in micro-engineering in 1991 and his Doctoral degree in 1997 at EPFL. During his thesis he co-founded the company K-Team, being both CEO and president of the company for about 5 years. He is one of the three main developers of the Khepera robot, considered as a standard in bio-inspired robotics and used by more than 1,000 universities and research centers worldwide. Fully back in research in 2000 and after a short period at CALTECH, he participated to the SWARM-BOTS project as the main developer of the s-bot robot platform, which was ranked on position 39 in the list of The 50 Best Robots Ever (fiction or real) by the Wired Journal in 2006. The SWARM-BOTS project was selected as FET-IST success story by the EU commission. He is author of more than 100 papers in the field of bio-inspired robotics and system level robot design. He is co-editor of several international conference proceedings. In November 2005 he received the EPFL Latsis University prize for his contributions to bio-inspired robotics. In 2011 he received the "Crédit Suisse Award for Best Teaching" from EPFL and in 2012 the "polysphère" award from the students as best teacher in the school of engineering. His interests include the development of innovative mechatronic solutions for mobile and modular robots, the creation of know-how for future embedded applications, and making robot platforms more accessible for education, research, and industrial development.

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.

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.

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.

Computer stereo vision

Computer stereo vision is the extraction of 3D information from digital images, such as those obtained by a CCD camera. By comparing information about a scene from two vantage points, 3D information can be extracted by examining the relative positions of objects in the two panels. This is similar to the biological process of stereopsis. In traditional stereo vision, two cameras, displaced horizontally from one another, are used to obtain two differing views on a scene, in a manner similar to human binocular vision.

Computer vision

Computer vision tasks include methods for , , and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context means the transformation of visual images (the input to the retina in the human analog) into descriptions of the world that make sense to thought processes and can elicit appropriate action.

Related lectures (64)

Deep Learning: Theory and Applications

Explores the mathematics of deep learning, neural networks, and their applications in computer vision tasks, addressing challenges and the need for robustness.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Neural Networks: Two Layers Neural Network

Covers the basics of neural networks, focusing on the development from two layers neural networks to deep neural networks.

Neural Networks: Multilayer Learning

Covers the fundamentals of multilayer neural networks and deep learning, including back-propagation and network architectures like LeNet, AlexNet, and VGG-16.

Machine Learning for Solving PDEs: Random Feature Method