Posts for year 2018
- Custom Data Loader
- Bibliography: Deep Learning With PyTorch
- Style Transfer
- Denoising Autoencoder
- Convolutional Autoencoder
- Simple Autoencoder
- Weight Initialization
- Transfer Learning Exercise
- Convolutional Layers in PyTorch
- CIFAR-10
- Visualizing Max Pooling
- Visualizing Convolving
- Custom Filters
- MNIST Multi-Layer Perceptron with Validation
- Dog Breed Classification
- MNIST MLP
- Dog Classification Project Overview
- Transfer Learning One More Time
- Tips, Tricks and Other Notes
- Part 8 - Transfer Learning
- Part 7 - Loading Image Data
- Part 6 - Saving and Loading Models
- Part 5 - Inference and Validation
- Part 4 - Classifying Fashion-MNIST
- Training Neural Networks
- Backpropagation Implementation (Again)
- Backpropagation
- Multi-Layer Perceptrons
- Training with Gradient Descent
- Gradient Descent (Again)
- Part 2 - Neural Networks in Pytorch
- Inspecting the Weights
- Further Noise Reduction
- Making the Network More Efficient
- Removing Noise
- Tensors In PyTorch
- The Sentiment Analyzer
- The Network Parts
- Exploring the Reviews Dataset
- Bike Sharing Project Feedback
- Sentiment Classification Lectures
- Notes on The Deep Learning Revolution
- Reading List
- Bike Sharing Project Answers
- The Bike Sharing Project
- Student Admissions
- Gradient Descent Practice
- Gradient Descent
- Compare and Learn
- Logistic Regression
- Multi-Class Cross Entropy
- Okay, but what about this deep-learning stuff?
- Maximum Likelihood
- One-Hot Encoding
- Softmax
- Non-Linear Regions
- The Perceptron Algorithm
- Perceptrons
- Introduction to Neural Networks
- NumPy Practice One
- How do you handle multiple inputs and outputs?
- How do you handle multiple outputs?
- How Do Neurons Work?
- How Do Machines Learn?