
A general introduction on course content and objectives
Explore how machine learning powers chatbot development, enabling natural language understanding and generation with supervised, unsupervised, and reinforcement learning, including naive Bayes, decision trees, SVM, neural networks.
Explore natural language processing for chatbot development, comparing bag of words and word embeddings, and detailing tokenization, vocabulary, stopwords, tf-idf, stemming, lemmatization, and transformers with self-attention for contextual meaning.
Explore large language model chatbots and prompt engineering to guide instruction, context, and data formats. Discover applications in code generation, information extraction, question answering, sentiment analysis, and future image understanding.
Learn to build rule-based chatbots with AIML, using an XML structure featuring ai ml, category, pattern, and template tags, plus wildcards, random, and predicates, tested in Python with VS Code.
Build a rule-based chatbot using AIML on Pandora Bots, test in real time, and craft greetings and topic-based conversations with predicates and fallbacks.
Learn a python-based workflow for machine learning model development: load data, perform EDA and cleaning, engineer features, split data, and evaluate classifiers like random forest and SVC on Titanic.
Build an intention prediction model for a chatbot using Python in a Jupyter notebook; vectorize text with a count vectorizer, train and validate multiple classifiers, and select the best model.
Develop a Python chatbot using Chatterbot and Flask, detailing environment settings, installing requirements.txt, training with the default English corpus and customized data, and building a user interface in VSCode.
Explore building a chatbot with ChatGPT, a leading large language model, covering GPT-3.5 and GPT-4, and using the UI playground for tasks like grammar, translation, and coding.
Learn prompt engineering to guide ChatGPT outputs, covering instruction, context, input data, and output indicators. Apply simple-to-complex prompts, clear commands, and explicit output formats with hash separators.
Implement a ChatGPT-based chatbot using the OpenAI API in Python, and deploy it as a public URL with the gradual library and open-source tools.
· Comprehensive Introduction: The course provides a comprehensive introduction to chatbot technology, covering its history, evolution, and real-world applications across different industries.
· Hands-on Approach: The course emphasizes practical learning through hands-on coding exercises, projects, and quizzes. You will gain valuable experience in building chatbots from scratch and applying various techniques.
· Integration with ChatGPT: Discover how to integrate ChatGPT, a cutting-edge language model developed by OpenAI, into your chatbot projects. Leverage its state-of-the-art language generation abilities to create dynamic and context-aware conversational agents.
· Industry-Relevant Skills: Gain industry-relevant skills that are in high demand. Chatbot technology is increasingly used in customer service, virtual assistants, marketing, and more. Enhance your employability and open doors to exciting career opportunities.
· Self-Paced Learning: The course is designed for self-paced learning, allowing you to progress at your own speed. Access the course materials and assignments anytime, anywhere, and learn at a comfortable pace that suits your schedule.
· Practical Applications: Explore real-world use cases and examples of chatbots in different industries. Understand how chatbot technology is revolutionizing customer interactions, improving efficiency, and enhancing user experiences.
The course teaching will be carried out in the following approaches:
Lecture Slides:
Provide conceptual overviews of chatbot development topics.Use visual aids, diagrams, and examples to aid understanding. Encourage student engagement through questions and discussions.
Live Coding Implementation:
Conduct live coding sessions and demonstrations. Walk students through practical implementation of chatbot techniques. Explain code rationale and decision-making process. Encourage students to follow along, ask questions, and participate.