This is a hands-on guide with Python example code that walks through the deployment of an ML-based search API using a simple 3-step approach. The article provides a deployment strategy applicable to most machine learning solutions, and the example code is available on GitHub.
A light-weight codebase that enables memory-efficient and performant finetuning of Mistral's models. It is based on LoRA, a training paradigm where most weights are frozen and only 1-2% additional weights in the form of low-rank matrix perturbations are trained.
An article discussing a simple and free way to automate data workflows using Python and GitHub Actions, written by Shaw Talebi.
This article introduces Google's top AI applications, providing a guide on how to start using them, including Google Gemini, Google Cloud, TensorFlow, Experiments with Google, and AI Hub.
Lambda Stack is an all-in-one package that provides a one line installation and managed upgrade path for deep learning and AI software, ensuring that you always have the most up-to-date versions of PyTorch, TensorFlow, CUDA, CuDNN, and NVIDIA Drivers.
Kolmogorov-Arnold Networks (KANs) and explains how to apply them for time series forecasting using Python. Basics of KANs and their connection to deep learning models such as the multilayer perceptron (MLP), which is used in state-of-the-art forecasting models.
• This is an MCU-based vision AI module powered by Arm Cortex-M55 and Ethos-U55, supporting TensorFlow and PyTorch frameworks.
• It has a standard CSI interface, onboard digital microphone, and SD card slot.
• Compatible with XIAO series, Arduino, Raspberry Pi, and ESP dev board.
• Supports off-the-shelf and custom AI models from SenseCraft AI, including Mobilenet V1, V2, Efficientnet-lite, Yolo v5 & v8.
• Can be used for industrial automation, smart cities, transportation, smart agriculture, and mobile IoT devices.
A simple and fast data pipeline foundation with sophisticated functionality.
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.
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.
Bookmarks on this page are managed by an admin user. 