Convolutional Neural Networks

This lecture introduces convolutional neural networks, focusing on their application in image and audio signal processing. It covers the concept of convolution, different types of filters used in signal processing, and how convolution is applied to both discrete and continuous signals. The lecture also discusses the importance of preserving spatial structures in images and the role of convolution in reducing the dimensionality of input data. Additionally, it explores various filter operations such as averaging, sharpening, smoothing, and derivative approximation, showcasing their impact on signal processing. The session concludes with a brief overview of extending convolution to 2D for image analysis and its role in neural networks.

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 (82)

Related concepts (39)

ME-390: Foundations of artificial intelligence

This course provides the students with 1) a set of theoretical concepts to understand the machine learning approach; and 2) a subset of the tools to use this approach for problems arising in mechanica

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.

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.

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.

Audio signal processing

Audio signal processing is a subfield of signal processing that is concerned with the electronic manipulation of audio signals. Audio signals are electronic representations of sound waves—longitudinal waves which travel through air, consisting of compressions and rarefactions. The energy contained in audio signals or sound level is typically measured in decibels. As audio signals may be represented in either digital or analog format, processing may occur in either domain.

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.

Convolutional Neural Networks: Fundamentals ME-390: Foundations of artificial intelligence

Covers the basics of Convolutional Neural Networks, including training optimization, layer structure, and potential pitfalls of summary statistics.

Neural Networks: Multilayer Learning PHYS-467: Machine learning for physicists

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

Kernel Methods: Neural Networks PHYS-467: Machine learning for physicists

Covers the fundamentals of neural networks, focusing on RBF kernels and SVM.

Deep Learning: Convolutional Neural Networks CS-233(a): Introduction to machine learning (BA3)

Covers Convolutional Neural Networks, standard architectures, training techniques, and adversarial examples in deep learning.

Ground Penetrating Radar: Data Analysis CIVIL-226: Introduction to machine learning for engineers

Explores the automated picking of reinforcement bars within Ground Penetrating Radar data using machine learning and signal processing techniques.