Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Do ImageNet Classifiers Generalize?

Description

This lecture explores the generalization of ImageNet classifiers, analyzing the progress over the past decade, safety-critical applications of machine learning, and the implications for evaluating machine learning models. It delves into the creation process of ImageNet, the three forms of overfitting, and the reliability of current machine learning models. The lecture also discusses the absence of overfitting in CIFAR-10 and ImageNet datasets, the robustness spectrum, and the future work needed to enhance robustness in machine learning. Various experiments and evaluations are presented, shedding light on the challenges and opportunities in the field of machine learning.

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

Official source

Related concepts (32)

Overfitting

In mathematical modeling, overfitting is "the production of an analysis that corresponds too closely or exactly to a particular set of data, and may therefore fail to fit to additional data or predict future observations reliably". An overfitted model is a mathematical model that contains more parameters than can be justified by the data. In a mathematical sense, these parameters represent the degree of a polynomial. The essence of overfitting is to have unknowingly extracted some of the residual variation (i.

Generalization error

For supervised learning applications in machine learning and statistical learning theory, generalization error (also known as the out-of-sample error or the risk) is a measure of how accurately an algorithm is able to predict outcome values for previously unseen data. Because learning algorithms are evaluated on finite samples, the evaluation of a learning algorithm may be sensitive to sampling error. As a result, measurements of prediction error on the current data may not provide much information about predictive ability on new data.

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.

Data analysis

Data analysis is the process of inspecting, cleansing, transforming, and modeling data with the goal of discovering useful information, informing conclusions, and supporting decision-making. Data analysis has multiple facets and approaches, encompassing diverse techniques under a variety of names, and is used in different business, science, and social science domains. In today's business world, data analysis plays a role in making decisions more scientific and helping businesses operate more effectively.

Data science

Data science is an interdisciplinary academic field that uses statistics, scientific computing, scientific methods, processes, algorithms and systems to extract or extrapolate knowledge and insights from noisy, structured, and unstructured data. Data science also integrates domain knowledge from the underlying application domain (e.g., natural sciences, information technology, and medicine). Data science is multifaceted and can be described as a science, a research paradigm, a research method, a discipline, a workflow, and a profession.

Related lectures (36)

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.

Model Assessment and Hyperparameter Tuning

Explores model assessment, hyperparameter tuning, and resampling strategies in machine learning.

Nonlinear ML Algorithms

Introduces nonlinear ML algorithms, covering nearest neighbor, k-NN, polynomial curve fitting, model complexity, overfitting, and regularization.

Specification Testing and Machine Learning

Explores specification testing, machine learning, overfitting, regularization, prediction tests, and variable selection.

Generalization Theory