Added placeholder for learning objectives

harvard-edge · Oct 5, 2023 · 52906d3 · 52906d3
1 parent 2db0088
commit 52906d3
Show file tree

Hide file tree

Showing 21 changed files with 170 additions and 5 deletions.
diff --git a/_quarto.yml b/_quarto.yml
@@ -2,7 +2,15 @@ project:
   type: book
   output-dir: _book
 
-abstract: Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+website:
+  comments: 
+    hypothesis:
+      theme: clean
+      openSidebar: true
+
+#abstract: Machine Learning Systems for TinyML offers comprehensive guidance on deploying machine learning on embedded devices. As edge computing and the Internet of Things proliferate, this textbook provides professionals and students the expertise to implement performant AI on resource-constrained hardware. A unique aspect of this book elucidates the entire machine learning workflow, from data engineering through training, optimization, acceleration, and production deployment. Key topics covered include deep learning and classical ML algorithms for embedded systems, efficient neural network architectures, hardware-aware training techniques, model compression, benchmarking for tinyML, and on-device learning. Additional chapters highlight cutting-edge advances like on-device data generation and crucial considerations around reliability, privacy, security, and responsible AI. With its rigorous approach spanning theory and practice across diverse tinyML application domains like smart homes, wearables, and industrial IoT, the book enables readers to develop specialized knowledge. Using concrete use cases and hands-on examples, readers will learn to apply machine learning to transform embedded and IoT systems. Overall, this indispensable guide provides a research-based foundation for leveraging machine learning in embedded systems.
+include-in-header:
+  text: <script src="https://hypothes.is/embed.js" async></script>
 
 book:
   page-navigation: true
@@ -80,6 +88,7 @@ format:
     theme: 
       - cosmo
       - style.scss
+    mainfont: Nunito
     code-link: true
     link-external-icon: true
     link-external-newwindow: true

diff --git a/ai_for_good.qmd b/ai_for_good.qmd
@@ -4,6 +4,13 @@ All of this technological discussion around embedded AI and TinyML we have been
 
 > The "AI for Good" movement plays a critical role in cultivating a future where an AI-empowered society is more just, sustainable, and prosperous for all of humanity.
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 To give ourselves a framework around which to think about AI for social good, we will be following the UN Sustainable Development Goals (SDGs). The UN SDGs are a collection of 17 global goals adopted by the United Nations in 2015 as part of the 2030 Agenda for Sustainable Development. The SDGs address global challenges related to poverty, inequality, climate change, environmental degradation, prosperity, and peace and justice. 

diff --git a/benchmarking.qmd b/benchmarking.qmd
@@ -1,5 +1,12 @@
 # Benchmarking AI
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 Explanation: Introducing the concept and importance of benchmarking sets the stage for the reader to understand why it is crucial in the evaluation and optimization of AI systems, especially in resource-constrained embedded environments where it is even more important! 

diff --git a/case_studies.qmd b/case_studies.qmd
@@ -1,3 +1,8 @@
 # Case Studies
 
-coming soon.
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
diff --git a/data_engineering.qmd b/data_engineering.qmd
@@ -1,5 +1,12 @@
 # Data Engineering
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 Explanation: This section establishes the groundwork, defining data engineering and explaining its importance and role in Embedded AI. A well-rounded introduction will help in establishing the foundation for the readers.

diff --git a/dl_primer.qmd b/dl_primer.qmd
@@ -1,6 +1,13 @@
 # Deep Learning Primer
 
-## Overview
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
+## Introduction
 
 ### Definition and Importance
 

diff --git a/efficient_ai.qmd b/efficient_ai.qmd
@@ -1,5 +1,12 @@
 # Efficient AI
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 In this chapter, we dive into the concepts that govern efficiency in AI systems. It is of paramount importance, especially in the context of embedded TinyML systems. The computational demands of neural networks can be overwhelming, even in the smallest of systems. Efficiency in AI isn't just a luxury---it's a necessity. For AI to truly be integrated into everyday devices and critical systems, it must operate within the constraints of limited resources without compromising its effectiveness. The drive for efficiency ensures that AI models are lean, fast, and sustainable, making their application viable across a broader range of platforms and scenarios. 

diff --git a/embedded_ml.qmd b/embedded_ml.qmd
@@ -4,6 +4,13 @@ Before delving into the intricacies of TinyML, it's crucial to grasp the distinc
 
 ![Cloud vs. Edge vs. TinyML: The Spectrum of Distributed Intelligence](images/cloud-edge-tiny.png)
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Cloud ML
 
 ### Characteristics

diff --git a/embedded_sys.qmd b/embedded_sys.qmd
@@ -4,6 +4,28 @@ In the domain of TinyML, embedded systems serve as the bedrock, providing a robu
 
 As we journey further into this chapter, we will demystify the intricate yet captivating realm of embedded systems, gaining insights into their structural design, operational features, and the crucial part they play in enabling TinyML applications. From an introduction to the fundamentals of microcontroller units to a deep dive into the interfaces and peripherals that amplify their capabilities, this chapter aims to be a comprehensive guide for understanding the nuanced aspects of embedded systems within the TinyML landscape.
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* Understand the definition, characteristics, history, and importance of embedded systems, especially in relation to tinyML. 
+
+* Examine the embedded system architecture including microcontrollers vs microprocessors, memory types and management, and System on Chip (SoC).
+
+* Explore embedded system programming including languages like C and Python, firmware development, and real-time operating systems (RTOS).
+
+* Discuss interfaces and peripherals like digital/analog I/O, communication protocols, etc. 
+
+* Analyze power management considerations, energy-efficient design, and battery management. 
+
+* Understand real-time characteristics of embedded systems including clocks, timing, task scheduling, and error handling. 
+
+* Evaluate security, reliability and safety-critical aspects of embedded systems. 
+
+* Identify future trends and challenges like edge computing, scalability, and market opportunities.
+
+:::
+
+
 ## Basics and Components
 
 ### Definition and Characteristics

diff --git a/ethics.qmd b/ethics.qmd
@@ -1,7 +1,16 @@
-# Responsible AI
+# Ethical AI
+
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
+## Responsible AI
 
 coming soon.
 
-# AI Safety
+## AI Safety
 
 coming soon.
diff --git a/frameworks.qmd b/frameworks.qmd
@@ -1,5 +1,12 @@
 # AI Frameworks
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 Explanation: Discuss what ML frameworks are and why they are important. Also, elaborate on the aspects involved in understanding how an ML framework is developed and deployed.

diff --git a/generative_ai.qmd b/generative_ai.qmd
@@ -1,5 +1,12 @@
 # Generative AI
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 I'll be candid - this chapter might be a bit of a leap. As of now, the concept of Generative AI in embedded systems is in its infancy. But I think it's crucial to take a stab at this emerging field, to anticipate the advancements and opportunities it holds for us in the future. It's a gamble, but one that could offer some food for thought into the future of AI technology.
 
 ![Generative AI Evolution](./images/generative_ai_evolution.png)

diff --git a/hw_acceleration.qmd b/hw_acceleration.qmd
@@ -1,5 +1,12 @@
 # AI Acceleration
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 Explanation: This section lays the groundwork for the chapter, introducing readers to the fundamental concepts of hardware acceleration and its role in enhancing the performance of AI systems, particularly embedded AI. This context is essential because hardware acceleration is a pivotal topic in the domain of embedded AI.

diff --git a/ondevice_learning.qmd b/ondevice_learning.qmd
@@ -1,5 +1,11 @@
 # On-Device Learning
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
 
 ## Introduction
 

diff --git a/ops.qmd b/ops.qmd
@@ -1,5 +1,12 @@
 # Embedded AIOps
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 Explanation: This subsection sets the groundwork for the discussions to follow, elucidating the fundamental concept of MLOps and its critical role in enhancing the efficiency, reliability, and scalability of embedded AI systems. It outlines the unique characteristics of implementing MLOps in an embedded context, emphasizing its significance in the streamlined deployment and management of machine learning models.

diff --git a/optimizations.qmd b/optimizations.qmd
@@ -1,5 +1,12 @@
 # Model Optimizations
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 This chapter stands as a critical overview of what is coming in the next few chapters that will offer readers an in-depth exploration of the multifaceted world of ML frameworks, highlighting their significance, functionalities, and the potential to revolutionize embedded systems development. As embedded devices continue to permeate various aspects of daily life, from healthcare to home automation, a comprehensive understanding of these frameworks not only serves as a bridge between concept and application but also as a catalyst in fostering innovations that are efficient, adaptable, and primed for the future.

diff --git a/privacy_security.qmd b/privacy_security.qmd
@@ -1,5 +1,12 @@
 # Privacy and Security
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 Explanation: In this section, we will set the stage for the readers by introducing the critical role of privacy and security in embedded AI systems. Understanding the foundational concepts is essential to appreciate the various nuances and strategies that will be discussed in the subsequent sections.

diff --git a/responsible_ai.qmd b/responsible_ai.qmd
@@ -1,5 +1,12 @@
 # Responsible AI
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 Explanation: In this introduction, we lay the groundwork by explicating the pivotal role of responsibility in AI, focusing on the integration of ethical considerations and accountability in the development and deployment of embedded AI systems.

diff --git a/style.scss b/style.scss
@@ -3,8 +3,17 @@
 $primary: #A51C30 !default;
 $font-size-root: 16px !default;
 
+@import url('https://fonts.googleapis.com/css2?family=Nunito:wght@400;800&display=swap');
+
+$border-color-left: #0dcaf0 !default;
+$icon: url('data:image/svg+xml,<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="bi bi-twitter" viewBox="0 0 16 16">  <path d="M5.026 15c6.038 0 9.341-5.003 9.341-9.334 0-.14 0-.282-.006-.422A6.685 6.685 0 0 0 16 3.542a6.658 6.658 0 0 1-1.889.518 3.301 3.301 0 0 0 1.447-1.817 6.533 6.533 0 0 1-2.087.793A3.286 3.286 0 0 0 7.875 6.03a9.325 9.325 0 0 1-6.767-3.429 3.289 3.289 0 0 0 1.018 4.382A3.323 3.323 0 0 1 .64 6.575v.045a3.288 3.288 0 0 0 2.632 3.218 3.203 3.203 0 0 1-.865.115 3.23 3.23 0 0 1-.614-.057 3.283 3.283 0 0 0 3.067 2.277A6.588 6.588 0 0 1 .78 13.58a6.32 6.32 0 0 1-.78-.045A9.344 9.344 0 0 0 5.026 15z"/></svg>') !default;
+
+$background-color: #bfe4eb !default;
+
 /*-- scss:rules --*/
 
+
+
 .sidebar-title {
   color: #A51C30;
 }

diff --git a/training.qmd b/training.qmd
@@ -1,5 +1,12 @@
 # AI Training
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Introduction
 
 Explanation: An introductory section sets the stage for the reader, explaining what AI training is and why it's crucial, especially in the context of embedded systems. It helps to align the reader's expectations and prepares them for the upcoming content.

diff --git a/workflow.qmd b/workflow.qmd
@@ -4,6 +4,13 @@ In this chapter, we'll explore the machine learning (ML) workflow, setting the s
 
 The ML workflow is a structured approach that guides professionals and researchers through the process of developing, deploying, and maintaining ML models. This workflow is generally divided into several crucial stages, each contributing to the effective development of intelligent systems.
 
+::: {.callout-note collapse="true"}
+## Learning Objectives
+
+* coming soon.
+
+:::
+
 ## Overview
 
 An ML workflow is a systematic process that encompasses the development, deployment, and maintenance of ML models. The typical steps involved are: