Category Machine learning

Artificial intelligence tools Artificial intelligence tools

Machine learning

A very noisy kitchen

Current artificial intellingence tools operate on complex modular architectures that transcend the basic language model. The essential technical components for their coordinated operation are reviewed, starting with the use of embeddings and vector databases as a foundation for semantic search and the implementation of RAG (Retrieval Augmented Generation). Likewise, advanced orchestration mechanisms are examined, such as integrating external APIs, security Guardrails, and the development of autonomous agents and Fine-Tuning processes for specialization in specific domains.

Manuel Molina
03/17/2026

Machine learning

Neither you can

Human cognition is reexamined through the lens of machine learning, proposing stochastic determinism as a technical alternative to free will. By equating creativity with the temperature of generative models and learning with error minimization via gradient descent, it is concluded that biological and artificial intelligences operate under the same fundamental algorithmic logic.

Manuel Molina
02/24/2026

Machine learning, Statistics

Cooper’s bookshelf

Principal component analysis (PCA) is a statistical dimensionality reduction technique that transforms correlated variables into independent orthogonal components. Its purpose is to simplify complex data structures by maximizing explained variance and eliminating informational redundancy through methods such as singular value decomposition.

Manuel Molina
01/27/2026

Machine learning, Statistics

The doctor who diagnosed vampires

The post analyzes the problem of class imbalance in biomedical models and how overall accuracy can become useless when the minority class is the clinically relevant one. It explains which evaluation metrics are most appropriate and outlines the main strategies to handle imbalance, such as oversampling (SMOTE, ADASYN), selective undersampling (Tomek links), and ensemble methods that stabilize performance in low-prevalence scenarios.

Manuel Molina
12/02/2025

Machine learning, Sin categoría, Statistics

The sympathy of pendulums

The rationale for minimizing the sum of squared errors in linear regression, which is often presented as a simple choice of convenience, is discussed. A probabilistic perspective suggests that the least squares equation arises naturally from assuming that the model's residuals follow a normal distribution.

Manuel Molina
06/10/2025