Duration: 6 Weeks | Total Time: 36 Hours
Format: Live online sessions using Google meet or MS Teams with hands-on coding, mini-projects, and a capstone project by an industry expert.
Target Audience: College Students, Professionals in Finance, HR, Marketing, Operations, Analysts, and Entrepreneurs
Tools Required: Laptop with internet
Trainer: Industry professional with hands on expertise
Week 1: Introduction to Deep Learning (6 hrs)
Objective: Build foundational understanding of neural networks and their role in modern data science.
Topics Covered:
- What is Deep Learning and how it differs from Machine Learning
- Key Concepts: Neurons, Layers, Activation Functions
- Biological vs Artificial Neural Networks
- Deep Learning in Data Science Applications (vision, NLP, recommender systems)
- Setting up the Environment – TensorFlow, Keras, and PyTorch basics
- Hands-on: Build your first Neural Network using Keras
Week 2: Artificial Neural Networks (ANN) (6 hrs)
Objective: Develop a strong understanding of feedforward and backpropagation algorithms.
Topics Covered:
- Architecture of ANN: Input, Hidden, Output Layers
- Forward Propagation and Backpropagation
- Gradient Descent and Optimization Techniques (SGD, Adam, RMSProp)
- Loss Functions and Evaluation Metrics
- Overfitting & Underfitting, Regularization (Dropout, Batch Normalization)
- Hands-on: Predicting customer churn using ANN
Week 3: Convolutional Neural Networks (CNN) (6 hrs)
Objective: Learn how to process and analyze image data using CNNs.
Topics Covered:
- Concept of Convolution, Filters, Pooling, and Feature Maps
- CNN Architectures – LeNet, AlexNet, VGG, ResNet
- Data Augmentation and Transfer Learning
- Hyperparameter Tuning in CNNs
- Real-world Applications – Image Classification, Object Detection
- Hands-on: Build an image classifier using CNN in TensorFlow
Week 4: Recurrent Neural Networks (RNN) & LSTM (6 hrs)
Objective: Master deep learning for sequential and time-series data.
Topics Covered:
- Introduction to Sequential Data
- RNN Architecture and Vanishing Gradient Problem
- Long Short-Term Memory (LSTM) and GRU Networks
- Applications – Stock Prediction, Text Generation, Sentiment Analysis
- Sequence-to-Sequence Models
- Hands-on: Sentiment analysis using LSTM on IMDB dataset
Week 5: Advanced Architectures & NLP (6 hrs)
Objective: Explore transformers, attention mechanisms, and advanced NLP techniques.
Topics Covered:
- Understanding Attention Mechanism
- Transformer Architecture – Encoder & Decoder
- Introduction to BERT, GPT Models
- Word Embeddings: Word2Vec, GloVe, FastText
- NLP Applications: Text Classification, Named Entity Recognition
- Hands-on: Build a text classifier using BERT
Week 6: Generative Models & Capstone Project (6 hrs)
Objective: Implement generative and hybrid models and complete an end-to-end project.
Topics Covered:
- Autoencoders & Variational Autoencoders (VAE)
- Generative Adversarial Networks (GANs) and their Applications
- Deep Reinforcement Learning Overview
- Model Deployment (Flask/Streamlit/TensorFlow Serving)
- Capstone Project: Choose one –
- Image Caption Generator
- Fake News Detector
- GAN-based Image Generator
- Presentation & Review
Course Outcomes
By the end of this course, learners will be able to:
- Build, train, and optimize deep learning models using TensorFlow and PyTorch
- Apply CNNs and RNNs for image, text, and sequence data
- Understand and implement transformer-based models like BERT and GPT
- Deploy deep learning models into production environments
- Complete a full deep learning project for real-world data science applications
Tools & Technologies Used
- Programming: Python
- Frameworks: TensorFlow, Keras, PyTorch
- Libraries: NumPy, Pandas, Scikit-learn, Matplotlib, OpenCV
- Deployment: Flask / Streamlit
- Datasets: CIFAR-10, MNIST, IMDB, Custom Dataset
Here you can see Important Links:-
No comments:
Post a Comment