Deep Learning
Who this course is for?
Students who have basic knowledge of Python and ML
Those who want to dive deeper into Neural Networks & DL
Engineering students doing AI/ML-based final year projects
Professionals looking to master Deep Learning for real-world use
Anyone interested in building powerful AI models
Why take this course?
Learn how deep learning powers modern AI (vision, NLP, etc.)
Master CNNs, RNNs, and LSTMs from scratch
Work with TensorFlow and Keras, the industry-standard tools
Create real-world DL models with actual datasets
Prepares you for advanced AI projects and job-ready skills
What you will learn?
Neural Networks fundamentals: forward/backward pass
TensorFlow/Keras for building DL models
CNNs for image classification & object recognition
RNNs & LSTMs for sequential and text data
Transfer learning and fine-tuning pre-trained models
Hands-on projects: Digit recognition, Sentiment analysis, X-ray detection
Model tuning, optimization, and deployment basics
Deep Learning Specialization
1. Introduction to AI, ML & Data Science ● What is Artificial Intelligence ● What is Machine Learning and how it works ● Differences between AI, ML, DL & Data Science ● Real-world applications of AI & ML ● Career opportunities in AI/ML 2. Python Programming for AI/ML ● Python basics: variables, loops, conditions, functions ● Lists, dictionaries, tuples, and sets ● Numpy for numerical computing ● Pandas for data manipulation ● Matplotlib and Seaborn for data visualization 3. Data Handling & Preprocessing ● Reading datasets (CSV, Excel, JSON) ● Handling missing values ● Encoding categorical data ● Feature scaling: normalization & standardization ● Train-test split 4. Core Machine Learning Algorithms ● Supervised learning: Linear & Logistic Regression ● Unsupervised learning: K-Means, Hierarchical Clustering ● Decision Trees and Random Forest ● Support Vector Machines (SVM) ● Model evaluation: Accuracy, Precision, Recall, F1-Score
1. Neural Network Fundamentals ● What is a Neural Network? ● Activation functions: ReLU, Sigmoid, Softmax ● Forward propagation and cost function ● Backpropagation and gradient descent (conceptual) ● Building simple neural network from scratch 2. Using TensorFlow and Keras ● Introduction to TensorFlow and Keras ● Dense layers, input/output shape ● Compiling and training models ● Evaluating model performance ● Saving and loading DL models 3. Image Classification using CNNs ● What are Convolutional Neural Networks ● Filters, kernels, feature maps ● Pooling layers and Flattening ● CNN for MNIST digit classification ● Data augmentation and dropout 4. Sequence Models & RNNs ● What is a Recurrent Neural Network (RNN) ● Understanding sequential data ● LSTM (Long Short-Term Memory) ● Building Sentiment Analysis model ● Text generation using LSTM
1. Advanced Topics ● Transfer Learning using pre-trained models ● Model tuning: hyperparameter optimization ● Working with large datasets ● Introduction to GANs (Generative Adversarial Networks) ● Working with Google Colab and Jupyter Notebook 2. Deep Learning Projects ● Handwritten Digit Recognition (MNIST) ● Sentiment Analysis on movie reviews ● Pneumonia Detection using X-Ray images ● Final Capstone DL Project (student-selected topic) ● Resume-ready project code on GitHub