AI@UCI Workshop: 11/12/25 Linear Regression & Cross Validation

AI@UCI Workshop: 11/12/25 Linear Regression & Cross Validation

by Artificial Intelligence at UCI

Formal & Physical Sciences AI — Models & Research UYQArtificial intelligence (AI)UYQMMachine learning
🎙 Artificial Intelligence at UCI 👥 941 📅 November 13, 2025 ⏱ 90 min 👁 64 📄 tutorial 🧭 2026-08-16
Available in: English (current) Français

Keywords

linear regressiongradient descentfeature transformsregularizationcross-validation

Summary

This workshop, led by Aston and Shreya, covers key concepts in linear regression and cross-validation. It begins with a brief introduction to the PHIT program, then moves into a review of gradient descent variants (batch, stochastic, mini-batch) and the direct solution for optimal parameters. The main focus is on feature transforms to handle nonlinear data, and regularization to prevent overfitting. The session includes a visual demonstration and a coding example. The presentation is interactive, with questions from the audience, and aims to solidify understanding of these foundational machine learning techniques.

90 words

Critical Evaluation

Value of the Information & Strength of the Argument

The workshop provides a clear and accessible explanation of linear regression, gradient descent, and the importance of feature transforms and regularization. The argumentation is logical, building from the cost function to the gradient and then to optimization methods. The use of a quadratic dataset effectively illustrates the limitations of linear models and the need for feature transforms. The coding demonstration reinforces the concepts. However, the presentation lacks depth in mathematical derivations and does not provide empirical evidence or comparisons of different approaches.

91 words

Title / Content Match

The title accurately reflects the content: a workshop on linear regression and cross-validation, with a coding demonstration.

Quality & Reliability

7/10

The workshop provides a solid conceptual foundation in linear regression, gradient descent variants, feature transforms, and regularization, with a live coding demonstration. The presentation is clear and interactive, but lacks formal citations and rigorous mathematical derivations, and the video is a recording of a workshop rather than a peer-reviewed source.

Chapters

Contribution & Novelties

The workshop provides a practical introduction to linear regression and cross-validation, with a focus on conceptual understanding and hands-on coding. It is valuable for beginners in machine learning. For further exploration, consider the following:

83 words

Radar Profile

The radar profile shows high scores in quantity of information and technical level, indicating a content-rich tutorial. The quality of information and global reliability are slightly lower, reflecting the informal nature and lack of citations. Overall, the workshop is a solid educational resource for beginners.

Reliability 6/10