Artificial Intelligence Fundamentals

Learning Outcomes

• By the end of this course, participants will be able to:
• Understand the core concepts of AI and its real-world applications.
• Explain the architecture and components of artificial neural networks (ANNs) and convolutional neural networks (CNNs).
• Implement activation functions, optimization techniques, and regularization in neural networks.
• Build and train simple ANN and CNN models using datasets.
• Apply transfer learning with pre-trained models.
• Grasp fundamental NLP concepts and techniques, including text preprocessing, word embeddings, and sentiment analysis.
• Develop practical NLP models using libraries like NLTK and TextBlob.
• Complete hands-on projects to reinforce learning and demonstrate proficiency..

Prerequisites

• Basic programming knowledge in Python.
• Familiarity with high school-level mathematics (algebra and basic statistics).
• No prior AI experience required, but enthusiasm for technology is recommended.

Target Audience

• Students and recent graduates interested in AI and machine learning.
• Professionals seeking to upskill in AI for career advancement.
• Hobbyists and enthusiasts wanting to explore AI concepts practically.

Course Structure

Module 1: Overview of AI

• Subtopics:
  • Introduction to Artificial Intelligence
  • Need for AI
  • Applications of AI

Module 2: Introduction to Neurons

• Subtopics:
  • What is a Neuron?
  • Biological vs. Artificial Neurons
  • Understanding the basic concept

Module 3: Architecture of ANN

• Subtopics:
  • Introduction to Artificial Neural Network (ANN)
  • Structure and components of ANN
  • Types of Neural Networks

Module 4: Modules in ANN

• Subtopics:
  • Layers in ANN
  • Input, hidden, and output layers
  • Forward and backward propagation

Module 5: Activation Functions

• Subtopics:
  • Introduction to activation functions
  • Types of activation functions (ReLU, Sigmoid, Tanh)
  • Usage and importance

Module 6: Optimization Functions

• Subtopics:
  • Introduction to optimization functions
  • Types of optimization functions
  • Usage in training neural networks

Module 7: Cost Function

• Subtopics:
  • Understanding cost function
  • Types of cost functions
  • Calculating and minimizing the cost

Module 8: Dense Networks

• Subtopics:
  • Introduction to Dense Networks
  • Structure and working
  • Implementing dense layers in neural networks

Module 9: Regularization Techniques

• Subtopics:
  • Need for regularization
  • Types of regularization (L1, L2, Dropout)
  • Applying regularization to neural networks

Module 10: Gradient Descent

• Subtopics:
  • Introduction to Gradient Descent
  • Types of Gradient Descent (Batch, Stochastic, Mini-batch)
  • Convergence and optimization

Module 11: ANN (Artificial Neural Network)

• Subtopics:
  • Building a simple ANN model
  • Training and evaluating the model
  • Practical implementation with a dataset

Module 12: Introduction to CNN

• Subtopics:
  • Basic concepts of Convolutional Neural Network (CNN)
  • Difference between ANN and CNN
  • Applications of CNN

Module 13: CNN Architecture Building

• Subtopics:
  • Structure of CNN
  • Convolutional layers, pooling layers, and fully connected layers
  • Building a simple CNN model

Module 14: Transfer Learning

• Subtopics:
  • Introduction to Transfer Learning
  • Pre-trained models (VGG16, VGG19, ResNet50, InceptionV3)
  • Implementing transfer learning

Module 15: Introduction to NLP

• Subtopics:
  • Basic concepts of Natural Language Processing (NLP)
  • Applications of NLP
  • Overview of NLP models

Module 16: Simple NLP with NLTK

• Subtopics:
  • Introduction to NLTK library
  • Stemming and lemmatization
  • Regex, stop words, corpus, n-grams

Module 17: Bag of Words

• Subtopics:
  • Concept of Bag of Words
  • Count vectorization
  • Implementing Bag of Words in NLP

Module 18: TF-IDF

• Subtopics:
  • Introduction to Term Frequency-Inverse Document Frequency (TF-IDF)
  • Calculating TF-IDF
  • Usage in text analysis

Module 19: Word Embedding

• Subtopics:
  • Understanding Word Embedding
  • Importance of Word Embedding in NLP
  • Techniques for Word Embedding

Module 20: GloVe

• Subtopics:
  • Introduction to GloVe (Global Vectors for Word Representation)
  • Implementing GloVe
  • Applications of GloVe

Module 21: Word2Vec

• Subtopics:
  • Introduction to Word2Vec
  • Continuous Bag of Words (CBOW) and Skip-gram models
  • Implementing Word2Vec

Module 22: FastText

• Subtopics:
  • Introduction to FastText
  • Comparison with Word2Vec and GloVe
  • Implementing FastText

Module 23: Keyed Vectors

• Subtopics:
  • Introduction to Keyed Vectors
  • Usage in NLP
  • Implementing Keyed Vectors

Module 24: TextBlob

• Subtopics:
  • Introduction to TextBlob library
  • Basic operations with TextBlob
  • Sentiment analysis using TextBlob

Module 25: Practical Project 1

• Subtopics:
  • Building a simple ANN or CNN model
  • Training and evaluating the model
  • Documenting the process and results

Module 26: Practical Project 2

• Subtopics:
  • Implementing an NLP model
  • Processing text data and applying NLP techniques
  • Documenting the process and results

Delivery Mode

• Doubt Clearing in Real-time – get your questions solved instantly
• One-to-One Live Online Classes – personalized learning with direct mentor support
• Flexible Scheduling – choose timings as per your availability
• Interactive Sessions – no pre-recorded videos, all sessions are live & practical
• Hands-on Coding – real-time coding exercises and dataset practice during classes