emlearn is an open-source machine learning inference engine designed for microcontrollers and embedded devices. It supports various machine learning models for classification, regression, unsupervised learning, and feature extraction. The engine is portable, with a single header file include, and uses C99 code and static memory allocation. Users can train models in Python and convert them to C code for inference.
Learn how to build an efficient pipeline with Hydra and MLflow
This article explains permutation feature importance (PFI), a popular method for understanding feature importance in explainable AI. The author walks through calculating PFI from scratch using Python and XGBoost, discussing the rationale behind the method and its limitations.
This article provides an introduction to Mlflow, an open-source platform for end-to-end machine learning lifecycle management. The article focuses on using MLflow as an orchestrator for machine learning pipelines, explaining the importance of managing complex pipelines in machine learning projects.
This article discusses TinyLlama, an open-source project for a smaller language model with around 1.1B parameters, capable of complex tasks with less memory usage. The article covers implementation, testing, and performance analysis.
Learn about the new Amazon time series model, which you can use to forecast energy usage, traffic congestion, and weather.
Learn about the importance of evaluating classification models and how to use the confusion matrix and ROC curves to assess model performance. This post covers the basics of both methods, their components, calculations, and how to visualize the results using Python.
This GitHub repository contains a course on Large Language Models (LLMs) with roadmaps and Colab notebooks. The course is divided into three parts: LLM Fundamentals, The LLM Scientist, and The LLM Engineer. Each part covers various topics, including mathematics, Python, neural networks, instruction datasets, pre-training, supervised fine-tuning, reinforcement learning from human feedback, evaluation, quantization, new trends, running LLMs, building a vector storage, retrieval augmented generation, advanced RAG, inference optimization, and deployment.
