AI

Revisiting Non-separable Binary Classification and its Applications in Anomaly Detection

1 Mins read

The inability to linearly classify XOR has motivated much of deep learning. We revisit this age-old problem and show that linear classification of XOR is indeed possible. Instead of separating data between halfspaces, we propose a slightly different paradigm, equality separation, that adapts the SVM objective to distinguish data within or outside the margin. Our classifier can then be integrated into neural network pipelines with a smooth approximation. From its properties, we intuit that equality separation is suitable for anomaly detection. To formalize this notion, we introduce closing numbers, a quantitative measure on the capacity for classifiers to form closed decision regions for anomaly detection. Springboarding from this theoretical connection between binary classification and anomaly detection, we test our hypothesis on supervised anomaly detection experiments, showing that equality separation can detect both seen and unseen anomalies.


Source link

Related posts
AI

NVIDIA Researchers Introduce Flextron: A Network Architecture and Post-Training Model Optimization Framework Supporting Flexible AI Model Deployment

3 Mins read
Large language models (LLMs) such as GPT-3 and Llama-2 have made significant strides in understanding and generating human language. These models boast…
AI

Whispering Experts: Toxicity Mitigation in Pre-trained Language Models by Dampening Expert Neurons

1 Mins read
An important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that…
AI

International Conference on Machine Learning (ICML) 2024

4 Mins read
Apple is sponsoring the International Conference on Machine Learning (ICML) 2024, which is taking place in person from July 21 to 27…

 

 

Leave a Reply

Your email address will not be published. Required fields are marked *