Lecture

Adaptive Signal Processing: Filtering & Neural Networks

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

COM-202: Signal processing

Signal processing theory and applications: discrete and continuous time signals; Fourier analysis, DFT, DTFT, CTFT, FFT, STFT; linear time invariant systems; filter design and adaptive filtering; sampling; interpolation and quantization; image processing, ...

Description

This lecture introduces the foundational concepts of adaptive signal processing, focusing on the derivation of adaptive filters like the LMS filter. The instructor explains the importance of self-similarity in signals, the theory of stochastic processes, and the basics of machine learning. The lecture covers the use of gradient descent to minimize error surfaces, the LMS algorithm for adaptive filtering, and its application in echo cancellation systems. By using noisy gradients, the LMS algorithm can adapt to changing environments efficiently, making it a powerful tool in signal processing and neural network training.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Instructors (2)

Paolo Prandoni

I appeared about at the same time as the White Album and, upon being born, I immediately took the one and only sabbatical of my life, which lasted a leisurely four years. I then proceeded to be pre-schooled, schooled, middle- and high-schooled, college educated, and finally grad-schooled here at EPFL. As a kid I was fascinated by those expensive long-distance phone calls and so I specialized in communication systems. And then I did this and I did that. But do we really want to go into details? I thought so.

Yanina Yurina Shkel

Teaching & PhD PhD Students Serhat Emre Coban, Anuj Kumar Yadav, Cemre Çadir Courses Advanced probability and applications COM-417 In this course, various aspects of probability theory are considered. The first part covers the main theorems in the field (law of large numbers, central limit theorem), while the second part focuses on the theory of martingales and concentration inequalities. Signal processing COM-202 Signal processing theory and applications: discrete and cont

Official source

Related concepts (32)

Quantization (signal processing)

Quantization, in mathematics and digital signal processing, is the process of mapping input values from a large set (often a continuous set) to output values in a (countable) smaller set, often with a finite number of elements. Rounding and truncation are typical examples of quantization processes. Quantization is involved to some degree in nearly all digital signal processing, as the process of representing a signal in digital form ordinarily involves rounding. Quantization also forms the core of essentially all lossy compression algorithms.

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.

Filter (signal processing)

In signal processing, a filter is a device or process that removes some unwanted components or features from a signal. Filtering is a class of signal processing, the defining feature of filters being the complete or partial suppression of some aspect of the signal. Most often, this means removing some frequencies or frequency bands. However, filters do not exclusively act in the frequency domain; especially in the field of many other targets for filtering exist.

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.

Related lectures (64)

Neural Signals and Signal Processing

Explores neural signals, EMG control, muscle synergies, and HD-EMG for prosthetic devices.

Neural Signals and Signal Processing

Covers neural signals, brain enthusiasm, neuroimaging, and statistical analysis in neuroimaging studies.

Optimization of Neuroprosthetic Systems

Explores the optimization of neuroprosthetic systems, including sensory feedback restoration and neural stimulation strategies.

Ground Penetrating Radar: Data Analysis

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

Neural Signals and Signal Processing

Explores neuronal signals, brain organization, measurement techniques, and MRI principles.

Related concepts (32)

Quantization (signal processing)

Audio signal processing

Recurrent neural network

Filter (signal processing)

Neural network