The Introduction of AI and Machine Learning with Python
Dive into the concept of Artificial Intelligence and Machine Learning (ML) and learn how to implement advanced algorithms to solve real-world problems. This course will teach you the workflow of ML projects from data pre-processing to advanced model design and testing.By the end of the course the students will be able to:- Build a variety of AI systems and models.- Determine the framework in which AI may function, including interactions with users and environments.- Extract information from text automatically using concepts and methods from natural language processing (NLP).- Implement deep learning models in Python using TensorFlow and Keras and train them with real-world datasets.Detailed course outline:Introduction to AI. Introduction to AI and Machine Learning.. Overview on Fields of AI:. Computer Vision.. Natural Language Processing (NLP).. Recommendation Systems.. Robotics.. Project: Creation of Chatbot using traditional programming (Python revision).Understanding AI· Understanding how AI works.· Overview of Machine Learning and Deep Learning.· Workflow of AI Projects.· Differentiating arguments vs parameters.· Project: Implementing functions using python programming (Python revision).Introduction to Data Science· Introduction to Data Science.· Types of Data.· Overview of DataFrame.· Project: Handling DataFrame using python programming by learning various tasks including:. Importing Dataset. Data Exploration. Data Visualization. Data CleaningMachine Learning· Overview on Machine Learning Algorithms with examples.· Types of Machine Learning:. Supervised. Unsupervised. Reinforcement· Types of Supervised Learning:. Classification. Regression· Project: Training and deploying machine learning model to predict salary of future candidates using python programming.Supervised Learning - Regression· Understanding Boxplot and features of Boxplot function.· Understanding Training and Testing Data with train_test_split function.· Project: Creating a machine learning model to solve a regression problem of predicting weight by training and testing data using python programming.Supervised Learning - Binary Classification· Understanding Binary Classification problems.· Overview on Decision tree Algorithm.· Overview on Random Forest Algorithm.· Use of Confusion Matrix to check performance of the classification model.· Project: Implementing Decision tree and Random forest algorithm using python programming to train a classification model to predict diabetic patients, and using confusion matrix to check performance of both algorithms.Supervised Learning - Multi-class Classification· Understanding Multi-class Classification problems.· One-vs-One method.· One-vs-Many method.· Project: Implementing Logistic Regression algorithm with both One-vs-One and One-vs-Rest approach to solve a multi-class classification problem of Iris flower prediction. Also, evaluating performance of both approaches using confusion matrix.Unsupervised Learning - Clustering· Understanding Unsupervised Learning.· Use of Unsupervised learning.· Types of Unsupervised learning:. Clustering. Association· Working of KMeans Algorithm.· Use of Elbow method to determine K value.· Project: Standardising the data and implementing KMeans algorithm to form clusters in the dataset using python programming.Unsupervised Learning - Customer Segmentation· Understanding Customer Segmentation.· Types of characteristics used for segmentation.· Concept of Targeting.· Project: Implementing KMeans algorithm to segment customers into different clusters and analysing the clusters to find the appropriate target customers.Unsupervised Learning - Association Rule Mining.· Understanding Association problems.· Market Basket Analysis.· Working of Apriori Algorithm.· Key metrics to evaluate association rules:. Support. Confidence. Lift· Steps involved in finding Association Rules.· Project: Implement Apriori algorithm to generate association rules for Market Basket Analysis using python programming.Recommendation System - Content-Based· Understanding Recommendation Systems.· Working of Recommendation Systems.· Types of Recommendation Systems:. Content-based. Collaborative· Project: Building a content-based recommendation system using K Nearest Neighbour(KNN) algorithm to recommend a car to the customer based on their input of preferred car features.Recommendation System – Collaborative Filtering· Understanding Collaborative filtering technique.· Types of approaches in collaborative filtering:. User-based. Item-based· Project: Building a movie recommendation system using item-based collaborative filtering based on data from a movie rating matrix.Natural Language Processing - Sentiment Analysis· Natural Language Processing (NLP)· Applications of NLP· Fundamental NLP tasks.· Tokenization· Project: Creating a machine learning model that can predict the sentiment in a sentence (Application of NLP).Deep Learning - Computer Vision· Understanding Deep Learning.· Neural Networks and Deep Neural Networks.· Image Processing· Project: A neural network model is created for image recognition purposes to predict the digit written in images of hand-written digits.Image Classification- Bonus Class· Learn about pre-trained models.· ResNet50 model trained using ImageNet data.· Project: Use ResNet50 model to classify images (predicting what the image represents).