· ai
Deep Graph Contrastive Representation Learning
Overview Imagine a map of friends, streets, or web pages where each dot links to others—that is a network. Scientists proposed a simple idea: create two slight...
-
- · ai
Improved Baselines with Momentum Contrastive Learning
Overview Teaching computers to recognize patterns without labeled data—known as unsupervised learning—has become more accessible thanks to simple tweaks to the...
- · ai
Variational Graph Auto-Encoders
Overview Imagine a web of friends or a tangle of research papers. A computer can quietly learn the shape behind that web without being told what’s right. The m...
- · ai
Blind Source Separation for automatic speech recognition: How Machines Learn to Untangle Mixed Signals
Introduction In the real world, signals rarely arrive clean and isolated. Microphones capture overlapping voices, sensors record multiple physical phenomena at...
- · ai
The Machine Learning “Advent Calendar” Day 10: DBSCAN in Excel
DBSCAN shows how far we can go with a very simple idea: count how many neighbors live close to each point. The post The Machine Learning “Advent Calendar” Day 1...
- · ai
The Machine Learning “Advent Calendar” Day 9: LOF in Excel
In this article, we explore LOF through three simple steps: distances and neighbors, reachability distances, and the final LOF score. Using tiny datasets, we se...
- · ai
This AI Model Can Intuit How the Physical World Works
The V-JEPA system uses ordinary videos to understand the physics of the real world....
- · ai
Crack the Code with Intelligent K: Uncover Pattern Secrets in Your Data
Discovering Hidden Patterns with Intelligent K-Means Clustering As data scientists and machine learning practitioners, we often find ourselves faced with large...
- · ai
Discover Hidden Patterns with Intelligent K-Means Clustering
What is Clustering Clustering is a type of unsupervised machine learning technique that groups similar data points together. Clustering helps you automatically...
- · ai
The Machine Learning “Advent Calendar” Day 5: GMM in Excel
This article introduces the Gaussian Mixture Model as a natural extension of k-Means, by improving how distance is measured through variances and the Mahalanobi...
- · ai
[Paper] Anomaly Detection with Adaptive and Aggressive Rejection for Contaminated Training Data
Handling contaminated data poses a critical challenge in anomaly detection, as traditional models assume training on purely normal data. Conventional methods mi...