This course offers a foundational understanding of deep learning, covering essential mathematical concepts, Python programming basics, and fundamental neural network principles. Participants will learn about key topics such as linear algebra, calculus, activation functions, and optimization algorithms. Hands-on projects will reinforce learning, focusing on different applications. Advanced topics include convolutional and recurrent neural networks, transfer learning, and regularization techniques. By the course's end, students will have gained practical skills in implementing deep learning models, preparing them for real-world data analysis tasks and further exploration in the field. Whether beginners or seasoned professionals, learners will find this course valuable for mastering the fundamentals of deep learning in a concise and accessible format.
Registration link: https://docs.google.com/forms/d/e/1FAIpQLSf5mVid9fw8qWi14sidf7v6RT80UZq8Yt8YUw8Qf6NPmxLJQQ/viewform 
COURSE CONTENT
 
- Foundations of Mathematics
Linear Algebra: Matrices, Vectors, Operations, Calculus: Derivatives, Integrals, Chain Rule, Probability: Basics of Probability Theory
- Python Programming Basics
Introduction to Python Syntax and Data Structures, Control Structures and Functions, Libraries for Scientific Computing: NumPy, Pandas
- Fundamentals of Neural Networks
Artificial Neural Networks (ANNs): Concepts and Architecture, Feedforward Neural Networks: Structure and Training, Activation functions, Loss functions, Optimization Techniques, Backpropagation: Theory and Implementation
- Deep Learning Essentials
Backpropagation Algorithm: Understanding the Chain Rule in Calculus, Optimization Algorithms: Variants and Applications, Loss Function Selection and Comparison, Regularization Techniques: L1/L2 regularization, Dropout
- Convolutional Neural Networks (CNNs)
Introduction to Convolutional Layers and Filters, Architecture Overview: LeNet, AlexNet, VGG, ResNet, Transfer Learning Concepts and Applications, Image Pre-processing Techniques
- Recurrent Neural Networks (RNNs) and LSTMs
Sequential Data Modelling with RNNs, Addressing the Vanishing Gradient Problem, Introduction to Long Short-Term Memory Networks (LSTMs), Variants of LSTM Architectures.