Decentralized AI: Privacy, Fairness, and the Future of Machine Learning
A keynote on the convergence of federated learning, blockchain, and decentralized systems for privacy-preserving AI
Nov 1, 2024
Fragaria
Fragaria is a powerful and flexible Chain of Thought (CoT) reasoning API that leverages various Language Model (LLM) providers and incorporates Reinforcement Learning (RL) techniques to solve complex problems and answer intricate questions. Named after the botanical genus of strawberries, Fragaria pays homage to the famous “How many ‘r’s in strawberry?” problem, symbolizing its ability to tackle both simple and complex queries with equal finesse.
Oct 29, 2024
Tackling Data Imbalance in Federated Learning
How Fed-Focal Loss addresses one of the most challenging problems in distributed machine learning: handling imbalanced data across federated clients.
Sep 15, 2024
The AI Copyright Challenge: Building Legal Frameworks for Generative AI
As generative AI transforms content creation, we need new frameworks that respect copyright while enabling innovation. Here's how we can build them.
Aug 10, 2024
Why Deepfake Detection Needs Decentralization
As deepfake technology becomes more sophisticated, centralized detection approaches are failing. Here's why we need decentralized solutions.
Apr 18, 2024
Viz: QLoRA-based Copyright Marketplace
Viz introduces a novel marketplace framework that addresses copyright concerns in generative AI by leveraging QLoRA (Quantized Low-Rank Adaptation) techniques to create legally compliant AI models.
Mar 10, 2024
Deepfake Detection Network
A decentralized blockchain-based network for detecting deepfakes using dynamic algorithm management. This project addresses the growing challenge of synthetic media manipulation by leveraging distributed consensus and machine learning.
Jan 15, 2024
Curriculum generation using Autoencoder based continuous optimization
Abstract This paper presents a novel approach to curriculum learning that leverages autoencoder-based continuous optimization for generating effective training sequences. Curriculum learning, which structures the training process from easier to harder examples, has shown promise in improving model performance and convergence.
Jun 1, 2021
One Shot Audio to Animated Video Generation
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.
Feb 1, 2021
Fed-Focal Loss for Imbalanced Data Classification in Federated Learning
A presentation on applying Focal Loss to Federated Learning for handling imbalanced data classification
Jan 8, 2021