- Lectures: 169
- Students: 10
- Duration: 10 weeks
WHAT YOU WILL LEARN
Introduction to AI
Classification and Regression using supervised Learning
Predictive Analytics with Ensemble Learning
Detecting patterns with Unsupervised Learning
Building Recommended systems
Logic Programming
Heuristic Search Techniques
Genetic Algorithms
Building Games with AI
Natural Language processing
Probabilistic reasoning for Sequential Data
Building a Speech Recognizer
Object Detection and Tracking
Artificial Neural Networks
Reinforcement Learning
ENTRY PROFILE
Programming Skills in Python
Programming Algorithms, Discrete Mathematics & Optimisation Techniques.
Linear Algebra, Calculus, Statistics & Probability.
EXIT PROFILE & JOB OPPORTUNITIES
AI Programmer
Curriculum
- 3 Sections
- 169 Lessons
- 10 Weeks
Expand all sectionsCollapse all sections
- Overview10
- Basics150
- 3.1Applications of AI
- 3.2Branches of AI
- 3.3Defining intelligence using Turing Test
- 3.4Making machines think like humans
- 3.5Building rational agents
- 3.6General Problem Solver
- 3.7Building an intelligent agent
- 3.8Installing Python 3
- 3.9Installing packages
- 3.10Loading data
- 3.11Classification and Regression Using Supervised Learning
- 3.12Classification and Regression Using Supervised Learning
- 3.13Supervised versus unsupervised learning
- 3.14What is classification?
- 3.15Preprocessing data
- 3.16Label encoding
- 3.17Logistic Regression classifier
- 3.18Naïve Bayes classifier
- 3.19Confusion matrix
- 3.20Support Vector Machines
- 3.21Classifying income data using Support Vector Machines
- 3.22What is Regression?
- 3.23Building a single variable regressor
- 3.24Building a multivariable regressor
- 3.25Estimating housing prices using a Support Vector Regressor
- 3.26Predictive Analytics with Ensemble Learning
- 3.27Predictive Analytics with Ensemble Learning
- 3.28What is Ensemble Learning?
- 3.29What are Decision Trees?
- 3.30What are Random Forests and Extremely Random Forests?
- 3.31Dealing with class imbalance
- 3.32Finding optimal training parameters using grid search
- 3.33Computing relative feature importance
- 3.34Predicting traffic using Extremely Random Forest regressor
- 3.35Detecting Patterns with Unsupervised Learning
- 3.36Detecting Patterns with Unsupervised Learning
- 3.37What is unsupervised learning?
- 3.38Clustering data with K-Means algorithm
- 3.39Estimating the number of clusters with Mean Shift algorithm
- 3.40Estimating the quality of clustering with silhouette scores
- 3.41What are Gaussian Mixture Models?
- 3.42Building a classifier based on Gaussian Mixture Models
- 3.43Finding subgroups in stock market using Affinity Propagation model
- 3.44Segmenting the market based on shopping patterns
- 3.45Building Recommender Systems
- 3.46Building Recommender Systems
- 3.47Creating a training pipeline
- 3.48Extracting the nearest neighbors
- 3.49Building a K-Nearest Neighbors classifier
- 3.50Computing similarity scores
- 3.51Finding similar users using collaborative filtering
- 3.52Building a movie recommendation system
- 3.53Logic Programming
- 3.54What is logic programming?
- 3.55Understanding the building blocks of logic programming
- 3.56Solving problems using logic programming
- 3.57Installing Python packages
- 3.58Matching mathematical expressions
- 3.59Validating primes
- 3.60Parsing a family tree
- 3.61Analyzing geography
- 3.62Building a puzzle solver
- 3.63Heuristic Search Techniques
- 3.64Heuristic Search Techniques
- 3.65What is heuristic search?
- 3.66Constraint Satisfaction Problems
- 3.67Local search techniques
- 3.68Constructing a string using greedy search
- 3.69Solving a problem with constraints
- 3.70Solving the region-coloring problem
- 3.71Building an 8-puzzle solver
- 3.72Building a maze solver
- 3.73Genetic Algorithms
- 3.74Genetic Algorithms
- 3.75Understanding evolutionary and genetic algorithms
- 3.76Fundamental concepts in genetic algorithms
- 3.77Generating a bit pattern with predefined parameters
- 3.78Visualizing the evolution
- 3.79Solving the symbol regression problem
- 3.80Building an intelligent robot controller
- 3.81Building Games with Artificial Intelligence
- 3.82Using search algorithms in games
- 3.83Combinatorial search
- 3.84Minimax algorithm
- 3.85Alpha-Beta pruning
- 3.86Negamax algorithm
- 3.87Installing easyAI library
- 3.88Building a bot to play Last Coin Standing
- 3.89Building a bot to play Tic-Tac-Toe
- 3.90Building two bots to play Connect Fourâ„¢ against each other
- 3.91Building two bots to play Hexapawn against each other
- 3.92Natural Language Processing
- 3.93Natural Language Processing
- 3.94Introduction and installation of packages
- 3.95Tokenizing text data
- 3.96Converting words to their base forms using stemming
- 3.97Converting words to their base forms using lemmatization
- 3.98Dividing text data into chunks
- 3.99Extracting the frequency of terms using a Bag of Words model
- 3.100Building a category predictor
- 3.101Constructing a gender identifier
- 3.102Building a sentiment analyzer
- 3.103Topic modeling using Latent Dirichlet Allocation
- 3.104Probabilistic Reasoning for Sequential Data
- 3.105Probabilistic Reasoning for Sequential Data
- 3.106Understanding sequential data
- 3.107Handling time-series data with Pandas
- 3.108Slicing time-series data
- 3.109Operating on time-series data
- 3.110Extracting statistics from time-series data
- 3.111Generating data using Hidden Markov Models
- 3.112Identifying alphabet sequences with Conditional Random Fields
- 3.113Stock market analysis
- 3.114Building A Speech Recognizer
- 3.115Building A Speech Recognizer
- 3.116Working with speech signals
- 3.117Visualizing audio signals
- 3.118Transforming audio signals to the frequency domain
- 3.119Generating audio signals
- 3.120Synthesizing tones to generate music
- 3.121Extracting speech features
- 3.122Recognizing spoken words
- 3.123Object Detection and Tracking
- 3.124Object Detection and Tracking
- 3.125Installing OpenCV
- 3.126Frame differencing
- 3.127Tracking objects using colorspaces
- 3.128Object tracking using background subtraction
- 3.129Building an interactive object tracker using the CAMShift algorithm
- 3.130Optical flow-based tracking
- 3.131Face detection and tracking
- 3.132Eye detection and tracking
- 3.133Artificial Neural Networks
- 3.134Artificial Neural Networks
- 3.135Introduction to artificial neural networks
- 3.136Building a Perceptron based classifier
- 3.137Constructing a single layer neural network
- 3.138Constructing a multilayer neural network
- 3.139Building a vector quantizer
- 3.140Analyzing sequential data using recurrent neural networks
- 3.141Visualizing characters in an Optical Character Recognition database
- 3.142Building an Optical Character Recognition engine
- 3.143Reinforcement Learning
- 3.144Reinforcement Learning
- 3.145Understanding the premise
- 3.146Reinforcement learning versus supervised learning
- 3.147Real world examples of reinforcement learning
- 3.148Building blocks of reinforcement learning
- 3.149Creating an environment
- 3.150Building a learning agent
- Conclusion9
- 4.1Summary
- 4.2Deep Learning with Convolutional Neural Networks
- 4.3Deep Learning with Convolutional Neural Networks
- 4.4What are Convolutional Neural Networks?
- 4.5Architecture of CNNs
- 4.6Types of layers in a CNN
- 4.7Building a perceptron-based linear regressor
- 4.8Building an image classifier using a single layer neural network
- 4.9Building an image classifier using a Convolutional Neural Network