AI Workshop PPT.pptx

Introduction to Generative AI -Dr. Bhawna Sinha Department of Computer Science and Applications Patna Women’s College  Introduction to Artificial Intelligence Artificial Intelligence (AI) is a technology that enables computers and machines to simulate human intelligence and problem-solving capab...

Introduction to Generative AI -Dr. Bhawna Sinha Department of Computer Science and Applications Patna Women’s College  Introduction to Artificial Intelligence Artificial Intelligence (AI) is a technology that enables computers and machines to simulate human intelligence and problem-solving capabilities. It has seen many cycles of hype, with significant advancements in natural language processing (NLP) marked by the release of ChatGPT. Artificial Intelligence (AI), a term coined by emeritus Stanford Professor John McCarthy in 1955, was defined by him as “the science and engineering of making intelligent machines”. Machine learning (ML) provides machines the ability to automatically learn from data and past experiences to identify patterns and make predictions with minimal human intervention.  Natural Language Processing NLP enables computers and digital devices to recognize, understand and generate text and speech. Natural Language Processing (NLP) enables computers to understand and communicate with human language, impacting daily life through search engines, chatbots, voice-operated GPS systems, and digital assistants on smartphones.  Computer Vision A field of artificial intelligence (AI) that uses machine learning and neural networks to teach computers and systems to derive meaningful information from digital images, videos and other visual inputs. Google lens is one of the most used tool that uses computer vision technology. Other use cases include development of self driving vehicles, mask detection technology and exam proctoring services.  Large Language Model (LLMs) Large language models (LLMs) are a category of foundation models trained on immense amounts of data making them capable of understanding and generating natural language and other types of content to perform a wide range of tasks. LLMs represent a significant breakthrough in NLP and artificial intelligence and are easily accessible to the public through interfaces like Open AI’s Chat GPT-3 and GPT-4, Meta’s Llama models and Google Gemini. As they continue to evolve and improve, LLMs are poised to reshape the way we interact with technology and access information, making them a pivotal part of the modern digital landscape.  Generative Pre-trained Transformers (GPT) are a type of Large Language Model (LLM) that are designed to understand and Generative generate natural language content. Pre-trained They are trained on vast amounts of data, which allows them to perform a wide range of Transformers tasks related to language processing. (GPTs) GPT models, such as OpenAI's Chat GPT-3 and GPT-4, are known for their ability to generate coherent and contextually relevant text based on the input they receive. Prompt Engineering Prompt Engineering is the practice of designing and refining input queries (prompts) to guide an AI model, like GPT-4, to generate the desired output. It involves crafting specific, clear, and contextually appropriate prompts that maximize the model's ability to produce relevant and high-quality responses. Characteristics of Writing a Good Prompt Writing an effective prompt is essential for achieving the best results from an AI model. Here are some key characteristics and techniques for crafting good prompts: 1. Specificity and Clarity: Be Detailed: Provide clear and detailed instructions to minimize ambiguity and help the model understand exactly what you need. Avoid Vagueness: Avoid vague or general terms that can lead to irrelevant or unfocused responses. Example: Ineffective Prompt: "Tell me about history." Effective Prompt: "Describe the key events and significance of the American Civil War." Characteristics of Writing a Good Prompt 2. Context Setting: Include Background Information: Provide relevant context or background information to help the model understand the situation or subject matter. Define Roles: If applicable, specify the role or perspective the AI should adopt (e.g., as a teacher, doctor, or historian). Example: Ineffective Prompt: "Write a report." Effective Prompt: "As a science teacher, write a report on the importance of renewable energy sources for a high school audience."  Characteristics of Writing a Good Prompt 3. Format Specification: Indicate Structure: Specify the desired format or structure of the output (e.g., list, paragraph, essay, dialogue). Set Length Requirements: Mention any length constraints or preferences for the response. Example: Ineffective Prompt: "Explain photosynthesis." Effective Prompt: "In one paragraph, explain the process of photosynthesis, highlighting the roles of sunlight, chlorophyll, and carbon dioxide." Characteristics of Writing a Good Prompt 4. Providing Examples: Use Examples: Include examples to guide the model towards the desired style or content. Show Desired Output: Demonstrate what a good response looks like by providing sample outputs. Example: Ineffective Prompt: "Write a poem." Effective Prompt: "Write a poem about the changing seasons, similar in style to: 'The leaves turn gold and red, a vivid autumn bed.'" Characteristics of Writing a Good Prompt 5. Step-by-Step Instructions: Break Down Tasks: For complex queries, break down the task into smaller, manageable steps. Request Sequential Responses: Ask for a step-by-step explanation or sequentially structured information. Example: Ineffective Prompt: "How do you make a cake?" Effective Prompt: "Explain how to bake a chocolate cake step-by-step, starting with the ingredients and ending with the baking process." Applications of GPT models Content Creation: GPT models can generate articles, stories, poetry, and even code, aiding in creative processes and reducing the time needed for content development. Customer Service: They can power chatbots and virtual assistants, providing real-time assistance and customer support. Language Translation: GPT models can translate languages, making communication across language barriers more accessible. Education: They can be used as tutoring systems, offering personalized learning experiences and answering student queries. Research: GPT models can summarize research papers, making it easier to digest complex information.  InVideo.ai Convert educational articles and blog posts into engaging video lessons using the text-to-video feature. InVideo.ai is a powerful online video creation platform that allows users to create engaging videos quickly and efficiently. It is designed to be user-friendly, offering a range of features that cater to both beginners and experienced video creators.