Input Representation & Feature Engineering

About
Privacy
Disclaimer

Graph Chatbot

Related lectures (30)

Page 1 of 3

Transformations of Input or Output

Covers handling missing data, feature engineering, and output transformations in machine learning.

Data Driven Science: MODNet Methodology

Explores the MODNet methodology for material property predictions, emphasizing feature selection and supervised learning.

Landscape and Generalisation in Deep Learning

Explores the challenges and insights of deep learning, focusing on loss landscape, generalization, and feature learning.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Applied Machine Learning

Introduces applied machine learning concepts such as data collection, feature engineering, model selection, and performance evaluation metrics.

Learning Sparse Features: Overfitting in Neural Networks

Discusses how learning sparse features can lead to overfitting in neural networks despite empirical evidence of generalization.

Image Classification: Decision Trees & Random Forests

Explores image classification using decision trees and random forests to reduce variance and improve model robustness.

Machine Learning Biases

Covers the basics of machine learning, challenges in deployment, adversarial attacks, and privacy concerns.

Machine Learning at the Atomic Scale

Explores simple models, electronic structure evaluation, and machine learning at the atomic scale.

Applied Machine Learning: Features and Models

Explores data collection, feature selection, model building, and performance evaluation in machine learning, emphasizing feature engineering and model selection.