Devdiscourse

From transformers to microgrids: AI expands across critical energy infrastructure

What was once experimental research is now becoming operational backbone across modern energy systems. In the editorial ...
Communications of the ACM

Rethinking the Stack: AI-Native Operating Systems and Tools

The applications and systems that software developers use on a daily basis are evolving as AI quickly becomes integrated into workflows. At the same time, the number of AI-native apps optimized for ...
GitHub

Fine-tuning Automatic Speech Recognition (ASR) Models for Accented Speech

Automatic Speech Recognition (ASR) converts spoken language into text, widely utilized in applications like virtual assistants and transcription services. Traditional ASR relied on Hidden Markov ...
Devdiscourse

Advanced AI model pushes aviation toward data-driven decarbonization

Researchers have developed an advanced artificial intelligence (AI) framework designed to significantly improve the forecasting of carbon dioxide emissions in the aviation sector. ACGRIME is an ...
GitHub

Hyperoptax: Parallel hyperparameter tuning with JAX

Hyperoptax is still a WIP and the API is subject to change. There are many rough edges to smooth out. It is recommended to download specific versions or to download from source if you want to use it ...
IEEE

DERL: A Differential Evolution-Reinforcement Learning Framework for Efficient Hyperparameter Optimization in Hyperspectral Image Classification

Abstract: The performance of hyperspectral image (HSI) classifiers is highly sensitive to the configuration of their hyperparameters (HPs). However, manual tuning is inefficient and impractical, ...
IEEE

Impact of Hyperparameter Tunning in Hourly Solar Irradiance Forecasting by Using Machine Learning Techniques

Abstract: As the demand for renewable energy is increasing for power generation, the penetration of solar energy is also on the rise. However, as solar energy is highly uncertain, accurate prediction ...