CodeEmporium Courses

Depthwise Separable Convolutions - Explained

Discover how depthwise separable convolutions work, their computational advantages over standard convolutions, and implement them with practical code examples.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Computer Vision 101 - Neural Networks

Explore computer vision fundamentals through neural networks, covering eye structure, visual pathways, CNNs, object detection, and advanced architectures like ResNet and YOLO.

• YouTube
• 8 hours 47 minutes
• Self-Paced
• Free Video

The Math You Should Know for Machine Learning

Master essential mathematical concepts for machine learning including probability, linear regression, PCA, gradient descent, and neural network backpropagation.

• YouTube
• 4 hours 53 minutes
• Self-Paced
• Free Video

Deep Learning 101 - Zero to Hero for Deep Learning

Discover neural networks from scratch with hands-on implementation, backpropagation, optimizers, loss functions, and advanced techniques like transfer learning and NLP applications.

• YouTube
• 2 hours 29 minutes
• Self-Paced
• Free Video

Reinforcement Learning 101

Discover the fundamentals of reinforcement learning through multi-armed bandits, Q-learning, deep Q-networks, and policy optimization techniques used in modern AI systems.

• YouTube
• 2 hours 4 minutes
• Self-Paced
• Free Video

Transformers from Scratch

Master transformer neural networks by building complete architecture from scratch, including attention mechanisms, encoders, decoders, and practical translation applications.

• YouTube
• 4 hours 25 minutes
• Self-Paced
• Free Video

Probability Theory for Machine Learning

Master probability theory fundamentals for ML: random variables, distributions, PMFs, PDFs, and likelihood estimation in under 3 hours.

• YouTube
• 2 hours 33 minutes
• Self-Paced
• Free Video

Logistic Regression - Concept, Math and Code

Master logistic regression fundamentals through mathematical concepts, gradient descent, visualization techniques, and practical data preprocessing for ML applications.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

Deep Learning 201 - Mathematical Foundations

Dive into neural networks' mathematical foundations covering activation functions, optimizers, CNNs, RNNs, LSTMs, GANs, and VAEs with practical explanations.

• YouTube
• 2 hours 19 minutes
• Self-Paced
• Free Video

Fast R-CNN - Explained

Explore Fast R-CNN architecture, training methods, and inference techniques for improved object detection performance compared to original R-CNN networks.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Faster R-CNN Explained

Discover how Faster R-CNN revolutionizes object detection through its Region Proposal Network, making it significantly faster than previous R-CNN architectures while maintaining accuracy.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Deconvolution - What Do Networks Learn? Visualization and Code

Uncover what deep layers of convolutional neural networks actually learn through deconvolution visualization techniques with practical code examples and visual demonstrations.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Feature Pyramid Networks - Enhancing Convolutional Network Performance Explained

Discover how Feature Pyramid Networks enhance convolutional network performance for computer vision tasks, with practical code examples and implementation details.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

ResNet - Explained

Discover ResNet architecture and skip connections to solve vanishing gradients and performance degradation in deep neural networks with practical code examples.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

YOLO - You Only Look Once Object Detection Algorithm Explained

Discover YOLO V1 object detection network architecture, training process, loss functions, and advantages over R-CNN methods in computer vision applications.

• YouTube
• 24 minutes
• Self-Paced
• Free Video