Machine Learning header
Machine Learning header
Machine learning, a subfield of artificial Intelligence (AI) and computer science, is an important part of the growing field of data science. It focuses on the use of data and algorithms to imitate human learning and improve accuracy. UCI started earning international recognition for machine learning in the 1980s, in particular for the Machine Learning Repository launched in 1987 by Ph.D. student David Aha. This repository of databases, domain theories, and data generators is used by AI researchers around the globe for the empirical analysis of machine learning algorithms.

Fundamentals of Machine Learning for Predictive Data Analtyics

 
Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies
 
JOHN KELLEHER
 
The authors touch upon essential aspects of machine learning using ancedotal accounts and more complex theoretic, probabilistic, statstic, and optimization concepts.

Pattern Classification

 
Pattern Classification and Scene Analysis
 
RICHARD DUDA & PETER HART
 
Richard Duda and Peter Hart give a systematic account of major topics in pattern recognition, a field that uses machine learning algorithms to recognize patterns and refularities in data. From text to images, pattern recognition can recognize familiar patterns quickly and accurately.

Learning Machines

 
Learning Machines: Foundations of Trainable Pattern-Classifying Systems.
 
NILS NILSSON
 
Nil Nilsson’s monograph covers classifiers, functions, training methods and theorems, and layered and linear machines.
Professor Eric Sudderth

Professor Eric Sudderth

 
Photographer Unknown
 
Erik Sudderth is a professor of computer science and statistics and Chancellor's Fellow at UCI. Known for his work in computer vision and automated scene interpretation, he directs the Center for Machine Learning and Intelligent Systems as well as the Hasso Plattner Institute (HPI) Research Center in Machine Learning and Data Science at UCI.

Semi-Supervised Training of Topic Models

 
Semi-Supervised Prediction-Constrained Topic Models
 
MICHAEL HUGHES ET AL.
 
A machine learning technique called topic modeling uses a small number of training examples to reliably predict labels that can help users comprehend large sets of data, such as a news database or patient records. The approach described in this article was tested on text analysis and electronic health records tasks.
3D Scene Reconstruction with Multi-layer Depth and Epipolar Transformers.

Convolutional Neural Networks

 
3D Scene Reconstruction with Multi-layer Depth and Epipolar Transformers
 
DAEYUN SHIN ET AL.
 
Convolutional neural networks (CNNs) are used to perceive and identify 3D shapes, going beyond cataloging objects in 2D images.

UCI Machine Learning Repository

 
UCI Machine Learning Repository
 
DHEERU DUA AND CASEY GRAFF
 
The UCI Machine Learning Repository is a collection of databases, domain theories, and data generators used for the empirical analysis of machine learning algorithms.