AI for Software Engineers

Generative artificial intelligence (AI) focuses on creating models that can generate content such as text, images, or even multimedia. Unlike discriminative models that classify or label existing data, generative models operate by learning patterns from the provided data and producing novel outputs. You'll begin this course with an overview of generative. You will explore some notable examples of generative models, including OpenAI's ChatGPT and Google Bard. Next, you will look at the use of prompt engineering when interacting with AI chatbots. Then, you will then delve into the history and evolution of generative AI models including important milestones that culminated in the conversational agents that we work with today. Finally, you will explore the risks and ethical considerations associated with generative AI, such as unintentional use of copyrighted data, the use of personal data for training, and the creation of malicious deepfakes using AI. You will also learn how you can mitigate some of these risks while working with generative technologies.

Generative Pre-trained Transformer (GPT) models are advanced artificial intelligence (AI) systems designed to understand and generate human-like text based on the information they've been trained on. These models can perform a wide range of language tasks, from writing stories to answering questions, by learning patterns in vast amounts of text data. In this course, you will dive into the world of GPT models and the foundational models that are pivotal to the development of the GPT-n series. You will gain an understanding of the terminology and concepts that make GPT models outstanding in performing natural language processing tasks. Next, you will explore the concept of attention in language models and explore the mechanics of the Transformer architecture, the cornerstone of GPT models. Finally, you will explore the details of the GPT model. You will discover methods used to adapt these models for particular tasks through supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), and techniques such as prompt engineering and prompt tuning.

This course will demystify the world of artificial intelligence (AI) and machine learning (ML), taking you from foundational concepts to practical applications. You'll learn to distinguish AI and ML, explore how algorithms learn, and perform common tasks like classification and clustering. You will begin by learning to confidently distinguish between the broad umbrella of AI and the specific subset of ML, understanding how each contributes to the landscape of intelligent systems. Next, you'll explore the milestones that shaped AI. Then you will discover how to classify the diverse approaches of machine learning. Finally, you will explore the practical aspects of common machine learning problems. You'll learn the meaning of regression, classification, and clustering and how they're applied in real-world scenarios. Discover how to evaluate model performance and explore the workings of popular traditional models like linear regression and decision trees. You'll also be introduced to ensemble learning, where the "wisdom of the crowds" fuels even more accurate predictions.

Deep learning and neural networks have revolutionized various fields by enabling computers to automatically learn complex patterns from data. This led to breakthroughs in areas such as image recognition, natural language processing (NLP), and autonomous driving. In this course, you will compare and contrast traditional machine learning (ML) and deep learning models. You will see how deep learning models excel in automated feature extraction from raw data, tackling complex tasks with the power of vast datasets. You will explore the fundamental unit of deep learning, the neuron, and understand how it works. Next, you will explore the diverse neural network architectures designed for specific data types. You will learn how convolutional neural networks (CNNs) extract features from images and how recurrent neural networks (RNNs) are able to extract relationships in time-series data. Finally, you will explore how neural networks handle natural language processing. You will learn how attention-based models help models focus on crucial parts of the input data for enhanced predictions and how generative adversarial networks (GANs) work. You will also explore reinforcement learning, a machine learning technique where agents navigate uncertain environments to maximize rewards.

Generative artificial intelligence (GenAI) can create new content, such as text, images, and music. It is powered by machine learning (ML) models that have been trained on massive datasets of existing content. Prompt engineering is the process of designing and crafting prompts that guide generative AI models to produce the desired output. You will start this course by learning how you can leverage prompt engineering to improve your day-to-day and work-related tasks. Next, you will see examples of prompting in action with external generative AI chatbots such as ChatGPT, Google Bard, and Microsoft Bing Chat. As several of these tools may not be supported on many corporate devices, you will not be expected to create accounts on those platforms, but you will be able to apply the learnings and principles to any corporate conversational AI chatbot in similar ways.

Different types of prompts serve distinct purposes when interacting with language models. Each type enables tailored interactions, from seeking answers and generating code to engaging in creative storytelling or eliciting opinions. In this course, you will learn the four elements of a prompt: context, instruction, input data, and output format. Next, will also explore prompt categories, such as open-ended, close-ended, multi-part, scenario-based, and opinion-based. Finally, you will look at different types of prompts based on the output that they provide. You will use prompts that generate objective facts, abstractive and extractive summaries, classification and sentiment analysis, and answers to questions. You'll tailor prompts to perform grammar and tone checks, ideation and roleplay, and mathematical and logical reasoning.

Data generation prompts instruct language models to generate synthetic data, useful for creating datasets. Code generation prompts are used to produce code snippets or entire programs, aiding developers in coding tasks. Zero-shot prompts challenge models to respond to unfamiliar tasks, relying on their general knowledge. Few-shot prompts provide limited context to guide models in addressing specific tasks, enhancing their adaptability. You will start this course by working with data generation and code generation prompts. You will explore how to use starter code prompts, convert code from one language to another, and prompt models to explain a piece of code. Next, you will see how to leverage generative AI to debug your code and generate complex bits of code with step-by-step instructions. Finally, you will explore techniques to improve prompt performance.