Convolutional Neural Networks: Filters and Channels

This lecture covers the concept of weight sharing in convolutional neural networks, which allows for shift invariance and generalization of features between different locations in an image. It explains how adding zeros to boundaries maintains the input's dimensionality after convolution. The lecture also discusses the use of different filters and channels, highlighting the learnable parameters and hyper-parameters of convolutional layers. Additionally, it explores various data augmentation techniques such as rotation, cutout, noise addition, and blurring, referencing a framework for contrastive learning of visual representations.

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 (56)

Related concepts (38)

CS-433: Machine learning

Machine learning methods are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and pr

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.

Self-supervised learning

Self-supervised learning (SSL) is a paradigm in machine learning for processing data of lower quality, rather than improving ultimate outcomes. Self-supervised learning more closely imitates the way humans learn to classify objects. The typical SSL method is based on an artificial neural network or other model such as a decision list. The model learns in two steps. First, the task is solved based on an auxiliary or pretext classification task using pseudo-labels which help to initialize the model parameters.

Feature learning

In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.

Noise (electronics)

In electronics, noise is an unwanted disturbance in an electrical signal. Noise generated by electronic devices varies greatly as it is produced by several different effects. In particular, noise is inherent in physics and central to thermodynamics. Any conductor with electrical resistance will generate thermal noise inherently. The final elimination of thermal noise in electronics can only be achieved cryogenically, and even then quantum noise would remain inherent. Electronic noise is a common component of noise in signal processing.

Sodium channel

Sodium channels are integral membrane proteins that form ion channels, conducting sodium ions (Na+) through a cell's membrane. They belong to the superfamily of cation channels. They are classified into 2 types: In excitable cells such as neurons, myocytes, and certain types of glia, sodium channels are responsible for the rising phase of action potentials. These channels go through three different states called resting, active and inactive states.

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.

Convolutional Neural Networks: Basics and Techniques CS-433: Machine learning

Introduces Convolutional Neural Networks, explaining key concepts like convolution, pooling, normalization, data augmentation, weight decay, and dropout.

Convolutional Networks: Overview and Architecture PHYS-467: Machine learning for physicists

Covers the motivation and architecture of convolutional networks, from LeNet to AlexNet.

Convolutional Neural Networks PHYS-467: Machine learning for physicists

Explores Convolutional Neural Networks, focusing on layers, filters, pooling, and weight sharing.

Document Analysis: Topic Modeling DH-406: Machine learning for DH

Explores document analysis, topic modeling, and generative models for data generation in machine learning.