On-Device AI: The Complete TinyML Guide for Developers
Deploy, Optimize, and Run Neural Networks on Microcontrollers, Raspberry Pi, and Mobile Hardware — No Cloud RequiredBy Caroline Lennox
Length3h 22m
About this audiobook
Run Real AI on Tiny Hardware — No Cloud, No Latency, No Data Leaving the Device
Every cloud inference call costs money, leaks data, and stalls the moment the network drops. What if your models ran directly on a $10 microcontroller instead?
On-Device AI: The Complete TinyML Guide for Developers is a hands-on, code-first roadmap to deploying neural networks on microcontrollers, Raspberry Pi, and mobile hardware. Written for developers who understand the basics of machine learning but have never squeezed a model into kilobytes of RAM, it takes you from core concepts all the way to shipping a production system — one you can build and run yourself.
You won't just read about TinyML. You'll train models, quantize them to a fraction of their size, deploy them to real boards, and debug the failures that only happen on constrained hardware.
Inside the book, you'll learn how to:
Choose the right hardware for your workload — MCUs, DSPs, NPUs, and FPGAs — using a clear decision framework
Shrink models to fit with INT8/INT4 quantization, pruning, and knowledge distillation
Convert and deploy models to TensorFlow Lite and TensorFlow Lite Micro on Raspberry Pi, Arduino, and ESP32
Build real projects: image classification, person detection, wake-word spotting, and sensor anomaly detection
Optimize for production — balancing power, memory, and speed, with duty-cycling that stretches battery life from hours to months
Ship to mobile with TensorFlow Lite on Android and Core ML on iOS from a single model
Run a complete end-to-end system with over-the-air firmware updates and in-field quality monitoring
Every chapter is code-first, followed by clear explanations and exercises designed to break your assumptions and force you to debug real problems — the way you actually learn.
This book is for you if:
You write C, C++, or Python and have shipped (or want to ship) software to embedded systems
You know training, inference, and overfitting — but have never deployed a model to a microcontroller
You care about privacy, offline reliability, real-time response, and zero per-inference cost
Stop renting intelligence from the cloud. Start building AI that works anywhere — in tunnels, on factory floors, in the field, and off the grid.
Audiobook details
GenreTechnology
Length3 hrs 22 mins
Narrated byListen with 1,000+ voices
FormateBook with Audio
LanguageEnglish
Table of contents
1On-Device AI: The Complete TinyML Guide for Developers
31ESP32 Deployment with ESP-IDF and Arduino Core
2Chapter 1: Why On-Device AI Changes Everything
32Debugging Inference Failures on MCUs
3Cloud AI vs Edge AI: The Real Cost
33Chapter 7: On-Device Computer Vision
4The TinyML Hardware Landscape
34Image Classification vs Object Detection at the Edge
5Latency, Privacy, and Offline Reliability
35Person Detection with MobileNet V2 SSD
Show all chaptersShow less
6Who This Book Is For and How to Use It
36Camera Capture and Preprocessing Pipeline
7Chapter 2: Setting Up Your TinyML Development Environment
37Handling False Positives and Confidence Thresholds
8Python Environment and Dependencies
38Chapter 8: On-Device Audio and Keyword Spotting
9Raspberry Pi 4 Setup for ML
39PDM Microphone Capture on Arduino
10Arduino IDE and Board Support Packages
40MFCC Feature Extraction on MCU
11Edge Impulse CLI Quickstart
41Wake-Word Model: Training to Deployment
12Exercises
42Chapter 9: Anomaly Detection on Sensor Data
13Chapter 3: Neural Network Fundamentals for Constrained Hardware
43Anomaly Detection Patterns: Autoencoder vs Statistical
14Why Standard Deep Learning Models Are Too Big
44Building and Training the Autoencoder
15Quantization: INT8 and INT4
45Deployment on ESP32 with FreeRTOS
16Pruning, Knowledge Distillation, and Architecture Search
46Chapter 10: Optimizing for Production: Power, Memory, and Speed
17MobileNet, SqueezeNet, and MCU-Friendly Architectures
47Memory Layout: ROM vs RAM Trade-offs on MCUs
18Chapter 4: Training Your First TinyML Model
48Model Surgery: Removing Layers, Reducing Filters
19Dataset Preparation and Augmentation
49Duty-Cycling and Sleep Modes for Battery Life
20Building and Training with Keras
50Profiling with ARM Keil and GCC Toolchain
21Exporting to TFLite Flatbuffer
51Chapter 11: On-Device AI on Mobile: Android and iOS
22Post-Training Quantization in Practice
52TFLite Android API: Interpreter and Task Library
23Chapter 5: Deploying Models on Raspberry Pi
53Core ML Model Conversion with coremltools
24TFLite Python Interpreter: Load, Allocate, Infer
54iOS Inference with Vision and Core ML Frameworks
25Real-Time Camera Inference Pipeline
55Cross-Platform Strategy: One Model, Two Platforms
26Coral USB Accelerator and Edge TPU Compilation
56Chapter 12: Building a Production TinyML System End-to-End
27Profiling with perf and TFLite Benchmark Tool
57• • • • System Architecture: Data Train Quantize Deploy Monitor
28Chapter 6: Deploying Models on Arduino and ESP32
58OTA Firmware Updates with ESP-IDF and AWS IoT
29TFLite Micro Architecture and Memory Model
59Monitoring Inference Quality in Production
30Arduino Nano 33 BLE Sense: IMU Gesture Recognition
60About the Author
More from Caroline Lennox
LiftoffEric Berger9h 4m$29 · $0.00
ApolloCharles Murray, Catherine Bly Cox18h 15m$30
Improvised Weapons and Munitions - The Official U.S. Army ManualU.S. Department of the Army4h 38m$2 · $0.00
Frosty: The incredible true story of the boy from Doonside who became a Bathurst kingMark Winterbottom8h 9m$26 · $0.00
Cadillac Desert, Revised and Updated EditionMarc Reisner27h 56m$30
The Honey BusMeredith May9h 31m$25 · $0.00
Operation PedestalMax Hastings12h 29m$29 · $0.00
When the Heavens Went on SaleAshlee Vance18h 20m$40 · $0.00
Hands of TimeRebecca Struthers8h 8m5.0 (1)$26 · $0.00
Everybody Has a Podcast (Except You)Justin McElroy, Travis McElroy, Griffin McElroy5h 9m$24 · $0.00
The Collected WorksNikola Tesla50h 9m$1 · $0.00
Never Lost AgainBill Kilday10h 1m$29 · $0.00
How the Internet HappenedBrian McCullough13h 28m$23 · $0.00
Collected Writings of Nikola TeslaNikola Tesla, Thomas Commerford Martin21h 50m$1 · $0.00
Just AspireAjai Chowdhry9h 13m$29 · $0.00
The Little Book of AliensAdam Frank8h 20m$26 · $0.00
The inventions, researches and writings of Nikola Tesla (Annotated)Thomas Commerford Martin16h 59m$2 · $0.00
KargilV.P. Malik15h 18m$24 · $0.00
Fire on the HorizonTom Shroder, John Konrad8h 23m$26 · $0.00
The Smell of Kerosene (Annotated)National Aeronautics and Space Administration, Donald L. Mallick, Peter W. Merlin11h 32m$2 · $0.00