#Machine Learning

Ten entries on this site carry the Machine Learning tag: two papers, three posts, three projects and two talks, dated between 2021 and 2024.

Papers

Curriculum generation using Autoencoder based continuous optimization
Paper · 2021 · arXiv This paper presents a novel approach to curriculum learning that leverages autoencoder-based continuous optimization for generating effective training sequences.
One Shot Audio to Animated Video Generation
Paper · 2021 · arXiv We present a novel approach for generating animated videos from single images using audio as the driving signal. Our method allows for the creation of realistic talking head animations by combining a single source image with an audio input.

Tackling Data Imbalance in Federated Learning
Post · 2024 How Fed-Focal Loss addresses one of the most challenging problems in distributed machine learning: handling imbalanced data across federated clients.
The AI Copyright Challenge: Building Legal Frameworks for Generative AI
Post · 2024 As generative AI transforms content creation, we need new frameworks that respect copyright while enabling innovation. Here's how we can build them.
Why Deepfake Detection Needs Decentralization
Post · 2024 As deepfake technology becomes more sophisticated, centralized detection approaches are failing. Here's why we need decentralized solutions.

Fragaria
Project · 2024 Advanced Chain of Thought (CoT) Reasoning API with Reinforcement Learning (RL)
Viz: QLoRA-based Copyright Marketplace
Project · 2024 A QLoRA-based Marketplace Framework for Legally Compliant Generative AI
Deepfake Detection Network
Project · 2024 Decentralized Deepfake Detection Blockchain Network using Dynamic Algorithm Management

Decentralized AI: Privacy, Fairness, and the Future of Machine Learning
Talk · 2024 · AI & Web3 Summit 2024 A keynote on the convergence of federated learning, blockchain, and decentralized systems for privacy-preserving AI
Fed-Focal Loss for Imbalanced Data Classification in Federated Learning
Talk · 2021 · International Workshop on Federated Learning for User Privacy and Data Confidentiality (FL-IJCAI'20) A presentation on applying Focal Loss to Federated Learning for handling imbalanced data classification