Feature learning | EPFL Graph Search

Are you an EPFL student looking for a semester project?

Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.

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. However, real-world data such as images, video, and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms. Feature learning can be either supervised, unsupervised or self-supervised. In supervised feature learning, features are learned using labeled input data. Labeled data includes input-label pairs where the input is given to the model and it must produce the ground truth label as the correct answer. This can be leveraged to generate feature representations with the model which result in high label prediction accuracy. Examples include supervised neural networks, multilayer perceptron and (supervised) dictionary learning. In unsupervised feature learning, features are learned with unlabeled input data by analyzing the relationship between points in the dataset. Examples include dictionary learning, independent component analysis, matrix factorization and various forms of clustering. In self-supervised feature learning, features are learned using unlabeled data like unsupervised learning, however input-label pairs are constructed from each data point, which enables learning the structure of the data through supervised methods such as gradient descent. Classical examples include word embeddings and autoencoders. SSL has since been applied to many modalities through the use of deep neural network architectures such as CNNs and transformers.

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 publications (11)

Related people (4)

Related concepts (22)

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.

k-means clustering is a method of vector quantization, originally from signal processing, that aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean (cluster centers or cluster centroid), serving as a prototype of the cluster. This results in a partitioning of the data space into Voronoi cells. k-means clustering minimizes within-cluster variances (squared Euclidean distances), but not regular Euclidean distances, which would be the more difficult Weber problem: the mean optimizes squared errors, whereas only the geometric median minimizes Euclidean distances.

Related courses (66)

Related lectures (590)

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 imple

PHYS-467: Machine learning for physicists

Machine learning and data analysis are becoming increasingly central in sciences including physics. In this course, fundamental principles and methods of machine learning will be introduced and practi

ME-390: Foundations of artificial intelligence

This course provides the students with basic theory to understand the machine learning approach, and the tools to use the approach for problems arising in engineering applications.

Flow-based generative models have become an important class of unsupervised learning approaches. In this work, we incorporate the key ideas of renormalization group (RG) and sparse prior distribution

IOP Publishing Ltd2022

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation

Pascal Fua, Mathieu Salzmann, Helge Jochen Rhodin, Victor Constantin, Sina Honari

In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contra

2022

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.

Chen Liu

In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning.However, they are shown vulnerable against adversarial attacks: well-designed, yet impercep

EPFL2022

Gradient Descent: Optimization

Explains gradient descent for optimization and how to find the direction towards the solution by minimizing distances.

Trajectory Forecasting in Autonomous Vehicles CIVIL-459: Deep learning for autonomous vehicles

Explores trajectory forecasting in autonomous vehicles, focusing on deep learning models for predicting human trajectories in socially-aware transportation scenarios.

Generative Models: Trajectory Forecasting CIVIL-459: Deep learning for autonomous vehicles

Explores generative models for trajectory forecasting in autonomous vehicles, including discriminative vs generative models, VAES, GANS, and case studies.