Lecture

Understanding ImageNet Classifiers

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.

Description

This lecture explores the generalization of ImageNet classifiers over the past decade, analyzing the progress made and the impact of key papers in machine learning and computer vision. It delves into the creation process of ImageNet, the challenges faced in achieving reliable machine learning models, and the implications for evaluating machine learning models beyond the i.i.d. setting. The lecture also discusses the robustness of machine learning models to adversarial attacks and distribution shifts, highlighting the importance of measuring robustness and promoting reliable engineering practices.

Official source

Related concepts (32)

Stable distribution

In probability theory, a distribution is said to be stable if a linear combination of two independent random variables with this distribution has the same distribution, up to location and scale parameters. A random variable is said to be stable if its distribution is stable. The stable distribution family is also sometimes referred to as the Lévy alpha-stable distribution, after Paul Lévy, the first mathematician to have studied it. Of the four parameters defining the family, most attention has been focused on the stability parameter, (see panel).

Robust statistics

Robust statistics are statistics with good performance for data drawn from a wide range of probability distributions, especially for distributions that are not normal. Robust statistical methods have been developed for many common problems, such as estimating location, scale, and regression parameters. One motivation is to produce statistical methods that are not unduly affected by outliers. Another motivation is to provide methods with good performance when there are small departures from a parametric distribution.

Lévy distribution

In probability theory and statistics, the Lévy distribution, named after Paul Lévy, is a continuous probability distribution for a non-negative random variable. In spectroscopy, this distribution, with frequency as the dependent variable, is known as a van der Waals profile. It is a special case of the inverse-gamma distribution. It is a stable distribution. The probability density function of the Lévy distribution over the domain is where is the location parameter and is the scale parameter.

Machine learning

Machine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.

Robust measures of scale

In statistics, robust measures of scale are methods that quantify the statistical dispersion in a sample of numerical data while resisting outliers. The most common such robust statistics are the interquartile range (IQR) and the median absolute deviation (MAD). These are contrasted with conventional or non-robust measures of scale, such as sample standard deviation, which are greatly influenced by outliers.

Related lectures (64)

Evaluating Machine Accuracy and Robustness on ImageNet

Explores the evaluation of machine and human accuracy and robustness on ImageNet, highlighting progress, challenges, and the need for improvement.

Machine Learning Fundamentals

Introduces fundamental machine learning concepts, covering regression, classification, dimensionality reduction, and deep generative models.

Do ImageNet Classifiers Generalize?

Examines the generalization of ImageNet classifiers, safety-critical applications, overfitting, and the reliability of machine learning models.

Introduction to Machine Learning

Covers the basics of machine learning for physicists and chemists, focusing on image classification and dataset labeling.

Document Analysis: Topic Modeling