Let's get started
Practical EndpointAI is here - Ambiq's Apollo4 Family of AI-capable devices enable high-performance AI capabilities while sipping power. Explore how to bring Speech UI, intelligent activity recognition, and real-time health analytics to your endpoint products.
Introducing AI at Ambiq
Learn the basics of how to use neuralSPOT to add AI features to your Apollo4 Plus applications, including how to integrate Tensorflow Lite for Microcontrollers, how feed sensor data to your AI models, and how to optimize for maximum performance at the lowest power possible.
Welcome to neuralSPOT
neuralSPOT is an AI-focused SDK and toolkit which makes using Apollo4's hardware capabilities easier than ever. neuralSPOT takes care of embedded platform details, letting your data scientists focus on AI.
Ambiq's AI Model Zoo is a library of reference AI models optimized for Apollo4 Plus, including Speech UI, sound classification and processing, activity recognition, and more.
ModelsView all 4 models
Heart Arrhythmia Classification
The Heart Arrhythmia Classification example model performs real-time heart arrhythmia classification using 1-lead ECG and optionally PPG. Classification can be performed on either rhythm (e.g. normal, AFIB, AFL) or beat (e.g. PAC, PVC).
Neural Network Speech
NN Speech (NNSP) integrates 3 neural networks, voice activitiy detection (VAD), keyword spotting (KWS) and Speech to intent (S2I).
Speech Enhancement and De-noising
End-to-end development and deployment reference implementation of an efficient speech enhancement and de-noising model.
TRAININGSView all videos
Accelerating the Development of Optimized AI Features with Ambiq’s neuralSPOT
Ambiq’s neuralSPOT® is an open-source AI developer-focused SDK designed for our latest Apollo4 Plus system-on-chip (SoC) family. neuralSPOT provides an on-ramp to the rapid development of AI features for our customers’ AI applications and products. Included with neuralSPOT are Ambiq-optimized libraries, tools, and examples to help jumpstart AI-focused applications.
Using neuralSPOT to Ease Embedded AI Development
Ambiq's VP of Artificial Intelligence, Carlos Morales shows how to use neuralSPOT to connect the evaluation board (EVB) to your computer, and use it as an integrated component using remote procedure calls.
Downloading, Compiling, and Deploying AI on Apollo4 Using neuralSPOT
Carlos Morales shows how to use neuralSPOT to get a sample AI model running on Apollo4. This process will require an Apollo4 Plus evaluation board (EVB), and a microphone.
Ambiq AI GitHub Repository Introduction
Introduction to Ambiq AI repository (repo) in GitHub including source codes, models, SDK, and more. The main repos include neuralSPOT and Model Zoo. Learn more.
Understanding neuralSPOT via the Basic Tensorflow Example
In this article, we walk through a neuralSPOT example application using it as a guide for how to use the SDK to integrate, develop, and deploy sophisticated AI models on Apollo4.
This is a detailed list of the features spread out over neuralSPOT. If you'd like to see a new feature, please file an issue on the repo.
Deploying EdgeImpulse Models using neuralSPOT Nests
NeuralSPOT is designed to ease the integration of AI models from many sources. In this article, we walk through how to use neuralSPOT Nests to deploy one such external software package (EdgeImpulse C++ models) onto Apollo4 Plus.
Optimizing AI using neuralSPOT
This article focuses on optimizing the energy efficiency of inference using Tensorflow Lite for Microcontrollers (TLFM), but many of the techniques apply to any inference runtime.