As more organizations seek to harness the power of machine learning and neural networks to extract insights and build out product features, deep learning frameworks make it easier to build and train neural networks for your use case. PyTorch is an open-source deep learning framework which has its origins at Facebook and offers powerful flexible libraries that allows you to build and train neural networks easily.
PyTorch APIs are closely integrated with native-Python which makes its APIs intuitive and easy to follow for Python developers.
Here is what this course covers:
Neurons and neural networks: The basic functionality of a neuron and how neurons come together to build NNs
Gradient descent, forward and backward passes: The basic steps involved in training a neural network
PyTorch tensors: The building blocks used to store data in PyTorch
Autograd: The PyTorch library used to perform gradient descent
Regression and classification models: Build a NN to perform regression to predict air quality and perform classification on salary data
Convolution, Pooling and CNNs: Understand how the these layers mimic the visual cortex to identify images
Convolutional Neural Networks: Classify house number using CNNs
Recurrent Neural Networks: Predict language from names using RNNs
Transfer learning: Use the Resnet-18 pre-trained model to classify images
This course is built around hands on demos using datasets from the real world. You'll be analyzing air quality data, salary data, images of house numbers and names data in order to build your machine learning models.
Software used: PyTorch, Python 3
