Hi, I am Tylan O'Flynn.
I work out of Edmonton, Canada.
I have been involved in several startups that use machine learning algorithms to solve novel problems.
My main focus is on reinforcement learning incorporating deep neural networks as function approximators. If you have any questions, feel free to contact me. Particularly good questions will get a video made about them!
Browse Tylan O'Flynn's Lessons
showing 9 lessons...
Construct A Custom PyTorch Model by creating your own custom PyTorch module by subclassing the PyTorch nn.Module class
Use PyTorch's nn.ReLU and add_module operations to define a ReLU layer
Use PyTorch nn.Sequential and PyTorch nn.Conv2d to define a convolutional layer in PyTorch
Use PyTorch's nn.Sequential and add_module operations to define a sequential neural network container
Augment the CIFAR10 Dataset Using the TorchVision RandomHorizontalFlip (transforms.RandomHorizontalFlip) and RandomCrop (transforms.RandomCrop) Transforms
Use the Torchvision Transforms Parameter in the initialization function to apply transforms to PyTorch Torchvision Datasets during the data import process
Use Torchvision Transforms Normalize (transforms.Normalize) to normalize CIFAR10 dataset tensors using the mean and standard deviation of the dataset
Convert CIFAR10 Dataset from PIL Images to PyTorch Tensors by Using PyTorch's ToTensor Operation
Load the CIFAR10 dataset from PyTorch Torchvision and split it into a train data set and a test data set