Deep Learning

Table of Contents Automatic Differentiation Part 2: Implementation Using Micrograd Introduction What Is a Neural Network? Having Problems Configuring Your Development Environment? About micrograd Imports and Setup The Value Class Addition Compute Gradient Multiplication Compute Gradient Power Compute Gradient Negation…

Table of Contents Automatic Differentiation Part 1: Understanding the Math Introduction Jacobian Chain Rule Mix the Jacobian and Chain Rule Forward and Reverse Accumulations Forward Accumulation Reverse Accumulation Summary References Citation Information Automatic Differentiation Part 1: Understanding the Math In…

Table of Contents A Deep Dive into Transformers with TensorFlow and Keras: Part 3 Introduction Configuring Your Development Environment Having Problems Configuring Your Development Environment? Project Structure Config Dataset Attention Utility Functions Positional Encoding Feed Forward Rate Schedule Loss Accuracy…

Table of Contents A Deep Dive into Transformers with TensorFlow and Keras: Part 2 A Brief Recap The Land of Attention Connecting Wires Skip Connections Layer Normalization Feed-Forward Network Positional Encoding Summary Citation Information A Deep Dive into Transformers with…

Table of Contents CycleGAN: Unpaired Image-to-Image Translation (Part 1) Introduction Unpaired Image Translation CycleGAN Pipeline and Training Loss Formulation Adversarial Loss Cycle Consistency Summary Citation Information CycleGAN: Unpaired Image-to-Image Translation (Part 1) In this tutorial, you will learn about image-to-image…

Table of Contents A Deep Dive into Transformers with TensorFlow and Keras: Part 1 Introduction The Transformer Architecture Encoder Decoder Evolution of Attention Version 0 Version 1 Version 2 Problems Solution Scaling of the Dot Product Version 3 Version 4…

Table of Contents Neural Machine Translation with Luong’s Attention Using TensorFlow and Keras Introduction Configuring Your Development Environment Having Problems Configuring Your Development Environment? Project Structure Luong’s Attention Encoder Architecture Decoder Architecture Input Feeding Approach Implementing Luong’s Attention Summary Citation…

Table of Contents Neural Machine Translation with Bahdanau’s Attention Using TensorFlow and Keras Introduction Configuring Your Development Environment Having Problems Configuring Your Development Environment? Project Structure RNN Encoder-Decoder Learning to Align and Translate Encoder Decoder Code Walkthrough Configuring the Prerequisites…

Table of Contents Multi-Task Learning and HydraNets with PyTorch Solving a Multi-Task Learning Project Creating a Multi-Task DataLoader with PyTorch Data Dataset INIT LEN GET_ITEM DataLoaders Model Definition Training: Loss Functions Training Loop Conclusion Citation Information Multi-Task Learning and HydraNets…