Omar Alharbi

L12- The Transformer: Cross Attention

L11-The Transformer: Masked Multi-Head Attention (Decoder)

L10-The Transformer: (Add & Norm) and Position-Wise Feed Forward

L9-The Transformer: Multi-Head Attention

L8-The Transformer: Input Embeddings& Positional Encoding

L7-Encoder-Decodel Model with Attention

L6- Encoder-Decoder Model (Seq-to-Seq)

L5- RNN-based Language Models

L4- Long Short-Term Memory (LSTM)

L3-RNN Types

L2-Neural Network to RNN part 2

L1-Neural Network to RNN Part 1

L22- Convolutional Neural Network from Scratch using Numpy (Forward-Propagation)

L21- Convolutional Neural Network (Convolve over Volume)

L20- Convolutional Neural Network (with 2 Conv Layers)

L19- Convolutional Neural Network (Zero Padding)

L18- Convolutional Neural Network | part3(Edges & Dimensions)

L17- Convolutional Neural Network | part2

L16- Convolutional Neural Network | part1

L15- Python | The Sequential Model for Building a Neural Network

L14- numpy, TensorFlow, Keras, ScikitLearn

L13- Activation Functions (Relu | Dying Relu& Gradient Exploding)

L12- Activation Functions (Sigmoid & Tanh | Saturation & Gradient Vanishing)

L11- Python | Backpropagation (Softmax) | تطبيق عملي-الانتشار الخلفي (سوفت ماكس)

L10- Backpropagation with Sofmax derivatives | المشتقات في الانتشار الخلفي مع السوفت ماكس

L9- Multi-Class Neural Networks (Backpropagation/Softmax) | الشبكة العصبية (التصنيف متعدد الفئات)

L8- Multi-Class Neural Networks (Softmax) | الشبكة العصبية (التصنيف متعدد الفئات)

L7- Python | NN(Back Propagation) | تطبيق عملي-الانتشار الخلفي

L6- Neural Networks (Backpropagation 2) | الانتشار الخلفي_جزء ثاني

L5- Neural Network (Backpropagation 1) | الانتشار الخلفي_جزء أول