WalkSelf · AI, Tech & Engineering · AI & Machine Learning

Deep Learning

Dive into the world of artificial neural networks. Learn to build, train, and optimize deep learning models for complex tasks using frameworks like TensorFlow and PyTorch.

Deep Learning

PyTorch Classes for Flexible Model Training

Build PyTorch Models for Linear Regression with `nn.Module`

Loss, MSE, and Gradient Descent Fundamentals

Graph Neural Networks: Core Concepts and Graph Theory

MNIST Dataset Foundations: Data Prep for Digit Recognition in Python

Building a Three-Layer Neural Network Output Layer in Python

PyTorch Model Persistence: Saving, Loading, and Checkpointing

TensorFlow Data Parsing: Building Example Specs for Serialized Data

Keras Model Persistence: Saving, Loading, and Predicting

Practical Deep Learning Projects for Portfolio Building

NLP with TensorFlow: Building Text Embeddings for Sequential Models

Deep Learning Optimization with Optax in JAX

Rescaling Neural Network Outputs for MNIST Classification

Feature Scaling and Dataset Standardization in PyTorch

Gradient Descent and Weight Optimization in Python

Gradient Descent and Optimization for Neural Networks

Designing ResNet Blocks: Residual Learning in Deep CNNs

Building and Evaluating Binary Classification Models in PyTorch

Deep Learning Layer Configuration in TensorFlow

Binary Classification with PyTorch and Scikit-Learn

Visualizing Gradient Descent in PyTorch and NumPy

Training Neural Networks with PyTorch and the CIFAR10 Dataset

Keras Hyperparameter Tuning: Optimize Deep Learning Models

Weight Initialization in Neural Networks: Foundations of Random Tuning