Artificial Intelligence

Image

Artificial Intelligence

The course focuses on the basic and advanced concepts of artificial intelligence such as Deep Networks, Structured Knowledge, Machine Learning, Hacking, Natural Language Processing, Artificial and Conventional Neural Network, Recurrent Neural Network, Self-Organizing Maps, Boltzmann Machines, AutoEncoders, PCA, LDA, Dimensionality Reduction, Model Selection and Boosting. Further, the artificial intelligence course will help you target the best jobs in the market in the field and not only this you can certainly increase your chances of employability by gaining more knowledge on the associated technologies such as IoT and Robotics. As a fact of the matter, Artificial Intelligence is the simulation of human intelligence by machines and it includes learning, reasoning, self-correction, speech recognition, and machine vision. Artificial intelligence is clearly the future of technology and every company is taking a step ahead to use artificial intelligence to make their products better. It is extensively used in diverse sectors such as healthcare, business, education, finance, law, and manufacturing.

Target Audience

  • This course is ideal for individuals having interest in Artificial Intelligence, Machine Learning, or Deep Learning. In other words, this course is meaningful for Python Developers, Robotics Engineer, and Fresh Graduates.

Prerequisites

  • As such, there are no technical prerequisites for artificial intelligence. However, knowledge of python and mathematical aptitude will be beneficial.

Course Objectives

Becoming an Artificial Intelligence Engineer puts you on the path to an exciting, evolving career that is predicted to grow sharply into 2025 and beyond. Artificial intelligence and Machine Learning will impact all segments of daily life by 2025, with applications in a wide range of industries such as healthcare, transportation, insurance, transport and logistics and even customer service. The need for AI specialists exists in just about every field as companies seek to give computers the ability to think, learn and adapt.

 


 

Course Curriculum


Section 1 : Artificial Intelligence

  • An Introduction to Artificial Intelligence
  • History of Artificial Intelligence
  • Future and Market Trends in Artificial Intelligence
  • Intelligent Agents – Perceive-Reason-Act Loop
  • Search and Symbolic Search
  • Constraint-based Reasoning
  • Simple Adversarial Search (Game-Playing)
  • Neural Networks and Perceptrons
  • Understanding Feedforward Networks
  • Boltzmann Machines and Autoencoders
  • Exploring Backpropagation


Section 2 : Deep Networks and Structured Knowledge

  • Deep Networks/Deep Learning
  • Knowledge-based Reasoning
  • First-order Logic and Theorem
  • Rules and Rule-based Reasoning
  • Studying Blackboard Systems
  • Structured Knowledge: Frames, Cyc, Conceptual Dependency
  • Description Logic
  • Reasoning with Uncertainty
  • Probability & Certainty-Factors
  • What are Bayesian Networks? 
  • Understanding Sensor Processing
  • Natural Language Processing
  • Studying Neural Elements
  • Convolutional Networks
  • Recurrent Networks
  • Long Short-Term Memory (LSTM) Networks 


Section 3 : Machine Learning and Hacking

  • Machine learning
  • Reprise: Deep Learning
  • Symbolic Approaches and Multiagent Systems
  • Societal/Ethical Concerns
  • Hacking and Ethical Concerns
  • Behaviour and Hacking
  • Job Displacement & Societal Disruption
  • Ethics of Deadly AIs
  • Danger of Displacement of Humanity 
  • The future of Artificial Intelligence


Section 4 : Natural Language Processing

  • Natural Language Processing 
  • Natural Language Processing in Python
  • Natural Language Processing in R
  • Studying Deep Learning
  • Artificial Neural Networks
  • ANN Intuition
  • Plan of Attack
  • Studying the Neuron
  • The Activation Function
  • Working of Neural Networks
  • Exploring Gradient Descent
  • Stochastic Gradient Descent
  • Exploring Backpropagation


Section 5 : Artificial and Conventional Neural Network

  • Understanding Artificial Neural Network
  • Building an ANN
  • Building Problem Description
  • Evaluation the ANN
  • Improving the ANN
  • Tuning the ANN
  • Conventional Neural Networks
  • CNN Intuition
  • Convolution Operation
  • ReLU Layer
  • Pooling and Flattening
  • Full Connection
  • Softmax and Cross-Entropy 
  • Building a CNN
  • Evaluating the CNN
  • Improving the CNN
  • Tuning the CNN


Section 6 : Recurrent Neural Network

  • Recurrent Neural Network
  • RNN Intuition
  • The Vanishing Gradient Problem
  • LSTMs and LSTM Variations
  • Practical Intuition
  • Building an RNN
  • Evaluating the RNN
  • Improving the RNN
  • Tuning the RNN


Section 7 : Self-Organizing Maps

  • Self-Organizing Maps
  • SOMs Intuition 
  • Plan of Attack
  • Working of Self-Organizing Maps
  • Revisiting K-Means
  • K-Means Clustering
  • Reading an Advanced SOM
  • Building an SOM


Section 8 : Boltzmann Machines

  • Energy-Based Models (EBM)
  • Restricted Boltzmann Machine
  • Exploring Contrastive Divergence
  • Deep Belief Networks
  • Deep Boltzmann Machines
  • Building a Boltzmann Machine
  • Installing Ubuntu on Windows
  • Installing PyTorch


Section 9 : AutoEncoders

  • AutoEncoders: An Overview
  • AutoEncoders Intuition
  • Plan of Attack
  • Training an AutoEncoder
  • Overcomplete hidden layers
  • Sparse Autoencoders
  • Denoising Autoencoders
  • Contractive Autoencoders
  • Stacked Autoencoders
  • Deep Autoencoders


Section 10 : PCA, LDA, and Dimensionality Reduction

  • Dimensionality Reduction
  • Principal Component Analysis (PCA)
  • PCA in Python
  • PCA in R
  • Linear Discriminant Analysis (LDA)
  • LDA in Python
  • LDA in R
  • Kernel PCA
  • Kernel PCA in Python
  • Kernel PCA in R


Section 11 : Model Selection and Boosting

  • K-Fold Cross Validation in Python
  • Grid Search in Python
  • K-Fold Cross Validation in R
  • Grid Search in R
  • XGBoost
  • XGBoost in Python
  • XGBoost in R