Machine Learning
273 articles in this category (Page 10 of 12)
LinkedIn Achieves 90% Offline Cost Reduction with Real-Time Recommendation Architecture
LinkedIn reduced offline costs by 90% by migrating from batch-based recommendations to a real-time architecture leveraging dynamic scoring and decoupled pipelines.
Inside ChatGPT: Deconstructing "Attention Is All You Need" (Part 1)
This article explains the shift from Recurrent Neural Networks (RNNs) to the Transformer architecture, detailing the vanishing gradient problem and the core concepts of self-attention.
New IBM Granite 4 Models to Reduce AI Costs with Inference-Efficient Hybrid Mamba-2 Architecture
IBM’s Granite 4.0 family of small language models aims to deliver up to 70% reduction in RAM usage for long inputs and concurrent batches while maintaining competitive accuracy.
Google DeepMind’s WeatherNext 2 Uses Functional Generative Networks For 8x Faster Probabilistic Weather Forecasts
Google DeepMind’s WeatherNext 2 achieves 6.5% CRPS improvement over GenCast, delivering faster and more accurate probabilistic weather forecasts.
AI-Driven Software Delivery: Leveraging Lean, ChOP & LLMs to Create Effective Learning Experiences
QCon’s experiment delivered a certification program using AI, achieving an 89% ‘green’ satisfaction rating and demonstrating the power of RAG architectures.