diff --git a/data_engineering.qmd b/data_engineering.qmd index f252306e..b3de4ffc 100644 --- a/data_engineering.qmd +++ b/data_engineering.qmd @@ -1,5 +1,7 @@ # Data Engineering +![_DALL·E 3 Prompt: Illustration in a rectangular format with a cool blue color palette visualizing the Data Engineering process. Starting on the left with icons of raw data sources, they connect to a central hub symbolized by swirling gears and pipelines in shades of blue. This represents the transformation, cleaning, and storage processes. On the right, datasets in refined formats are symbolized by sleek database icons and a machine learning model. Flow lines in varying blue tones connect each element, emphasizing the transition and importance of each data engineering stage._](./images/cover_data_engineering.png) + Data is the lifeblood of AI systems. Without good data, even the most advanced machine learning algorithms will fail. In this section, we will dive into the intricacies of building high-quality datasets to fuel our AI models. Data engineering encompasses the processes of collecting, storing, processing, and managing data for training machine learning models. ::: {.callout-tip collapse="true"} diff --git a/dl_primer.qmd b/dl_primer.qmd index 3ee20490..d3360d15 100644 --- a/dl_primer.qmd +++ b/dl_primer.qmd @@ -1,5 +1,7 @@ # Deep Learning Primer +![_DALL·E 3 Prompt: Photo of a classic classroom with a large blackboard dominating one wall. Chalk drawings showcase a detailed deep neural network with several hidden layers, and each node and connection is precisely labeled with white chalk. The rustic wooden floor and brick walls provide a contrast to the modern concepts. Surrounding the room, posters mounted on frames emphasize deep learning themes: convolutional networks, transformers, neurons, activation functions, and more._](./images/cover_dl_primer.png) + This section offers a brief introduction to deep learning, starting with an overview of its history, applications, and relevance to embedded AI systems. It examines the core concepts like neural networks, highlighting key components like perceptrons, multilayer perceptrons, activation functions, and computational graphs. The primer also briefly explores major deep learning architecture, contrasting their applications and uses. Additionally, it compares deep learning to traditional machine learning to equip readers with the general conceptual building blocks to make informed choices between deep learning and traditional ML techniques based on problem constraints, setting the stage for more advanced techniques and applications that will follow in subsequent chapters. ::: {.callout-tip collapse="true"} diff --git a/embedded_ml.qmd b/embedded_ml.qmd index db4d2374..4006cc89 100644 --- a/embedded_ml.qmd +++ b/embedded_ml.qmd @@ -1,5 +1,7 @@ # Embedded AI +![_DALL·E 3 Prompt: Illustration in a rectangular format depicting the merger of embedded systems with Embedded AI. The left half of the image portrays traditional embedded systems, including microcontrollers and processors, detailed and precise. The right half showcases the world of artificial intelligence, with abstract representations of machine learning models, neurons, and data flow. The two halves are distinctly separated, emphasizing the individual significance of embedded tech and AI, but they come together in harmony at the center._](./images/cover_embedded_ai.png) + Before delving into the intricacies of TinyML, it's crucial to grasp the distinctions among Cloud ML, Edge ML, and TinyML. In this chapter, we'll explore each of these facets individually before comparing and contrasting them. ::: {.callout-tip collapse="true"} diff --git a/embedded_sys.qmd b/embedded_sys.qmd index f7f60ec2..7ab5300a 100644 --- a/embedded_sys.qmd +++ b/embedded_sys.qmd @@ -1,4 +1,6 @@ -## Embedded Systems +# Embedded Systems + +![_DALL·E 3 Prompt: Illustration of a modern smart device, like a wearable watch or smart thermostat, opened up to reveal its inner components. Within the device, there are tiny robots analyzing and tweaking the circuits. On the device's display, a machine learning model is being trained, showing data points and accuracy metrics, representing the convergence of embedded systems and AI._](./images/cover_embedded_sys.png) In the domain of TinyML, embedded systems serve as the bedrock, providing a robust platform where intelligent algorithms can function both efficiently and effectively. Defined by their specialized roles and real-time computational capabilities, these systems act as the convergence point where data and computation intersect on a micro-scale. Tailored to meet the demands of specific tasks, they excel in optimizing performance, energy usage, and spatial efficiency—key considerations in the successful implementation of TinyML solutions. diff --git a/images/cover_ai_workflow.png b/images/cover_ai_workflow.png new file mode 100644 index 00000000..74e2c8eb Binary files /dev/null and b/images/cover_ai_workflow.png differ diff --git a/images/cover_data_engineering.png b/images/cover_data_engineering.png new file mode 100644 index 00000000..35641f43 Binary files /dev/null and b/images/cover_data_engineering.png differ diff --git a/images/cover_dl_primer.png b/images/cover_dl_primer.png new file mode 100644 index 00000000..4c021821 Binary files /dev/null and b/images/cover_dl_primer.png differ diff --git a/images/cover_embedded_ai.png b/images/cover_embedded_ai.png new file mode 100644 index 00000000..5b9b1cac Binary files /dev/null and b/images/cover_embedded_ai.png differ diff --git a/images/cover_embedded_sys.png b/images/cover_embedded_sys.png new file mode 100644 index 00000000..4ed51e9e Binary files /dev/null and b/images/cover_embedded_sys.png differ diff --git a/workflow.qmd b/workflow.qmd index 3c4d3c22..7974a9ee 100644 --- a/workflow.qmd +++ b/workflow.qmd @@ -1,5 +1,7 @@ # AI Workflow +![_DALL·E 3 Prompt: Illustration in a rectangular format of a stylized flowchart representing the AI workflow chapter. Starting from the left, the stages include 'Data Collection' represented by a database icon, 'Data Preprocessing' with a filter icon, 'Model Design' with a brain icon, 'Training' with a weight icon, 'Evaluation' with a checkmark, and 'Deployment' with a rocket on the far right. Arrows connect each stage, guiding the viewer horizontally through the AI processes, emphasizing the sequential and interconnected nature of these steps._](./images/cover_ai_workflow.png) + In this chapter, we'll explore the machine learning (ML) workflow, setting the stage for subsequent chapters that delve into the specifics. To ensure we don't lose sight of the bigger picture, this chapter offers a high-level overview of the steps involved in the ML workflow. 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.