Section

Machine Learning

6 pieces · Artificial Intelligence, Machine Learning & Computing Research · Est. 2007

Machine Learning

Synthetic Training Data and Model Collapse: Where Self-Generated Data Helps and Where It Hurts

What the research on model collapse actually shows, why accumulating real data changes the outcome, and when verified synthetic data improves models.

By Institute for Joint Cognition & AI · 6 min · 3 November 2026

Machine Learning

Mixture-of-Experts Explained: Routing, Load Balancing, and Why Frontier Models Use Them

How mixture-of-experts models route tokens, why load balancing is the hard part, and the compute and memory trade-offs behind sparse frontier architectures.

By Institute for Joint Cognition & AI · 6 min · 27 October 2026

Machine Learning

Mollifier Layers: A New Way to Stabilize Neural Networks Solving Inverse PDEs

Recursive autodiff degrades badly for high-order derivatives on noisy data. Mollifier layers replace it with convolution against analytic smoothing kernels.

By Institute for Joint Cognition & AI · 6 min · 7 August 2026

Machine Learning

Hyperparameter Optimization: Grid Search, Bayesian Methods, and Population-Based Training

A technical comparison of grid search, random search, Bayesian optimization, and population-based training for tuning machine learning hyperparameters.

By Institute for Joint Cognition & AI · 12 min · 14 February 2024

Machine Learning

Parameter-Efficient Fine-Tuning: LoRA, QLoRA, and Adapters in Practice

How LoRA, QLoRA, and adapter modules cut fine-tuning cost by orders of magnitude, with the memory/quality trade-offs engineers actually hit in practice.

By Institute for Joint Cognition & AI · 12 min · 10 July 2023

Machine Learning

Transformer Architecture Explained: How Attention Actually Works

Transformer architecture explained for ML practitioners: attention, self-attention, Q/K/V, multi-head attention, positional encoding, and why transformers replaced RNNs.

By Institute for Joint Cognition & AI · 10 min · 15 May 2023