Learn By Example: PyTorch

Learn By Example: PyTorch

English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 3h 24m | 755 MB

Build and train neural networks using APIs and libraries from PyTorch

In this course you’ll learn about PyTorch APIs; these 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 descents
  • Regression and classification models: Build a NN to perform regression and predict air quality and perform classification on salary data
  • Convolution, pooling, and CNNs: Understand how these layers mimic the visual cortex to identify images
  • Convolutional Neural Networks: Classify house numbers 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 name data in order to build your machine learning models.

This course will teach you about neurons and neural networks in depth, with practical examples.

What You Will Learn

  • Understand how neurons and neural networks work.
  • Understand gradient descent and forward and backward passes in a NN
  • Work with PyTorch tensors to store and manipulate data
  • Build and train regression and classification neural network models using PyTorch
  • Use pre-trained models to harness the power of transfer learning
Table of Contents

You, This Course and Us
1 You, This Course and Us

Introduction To PyTorch And Neural Networks
2 Overview
3 Neurons And Neural Networks
4 Introducing PyTorch
5 Installation And Setup
6 The Computation Graph
7 Gradient Descent
8 Forward And Backward Passes

PyTorch Tensors
9 PyTorch Tensors
10 PyTorch Tensors Implementation – I
11 PyTorch Tensors Implementation – II
12 PyTorch Tensors Implementation – III

Gradient Descent And Autograd
13 Gradients, A Vector Of Partial Derivatives
14 Autograd
15 Reverse Mode Auto Differentiation
16 Linear Regression Using Autograd

Regression and Classification
17 Regression To Predict Air Quality
18 Regression To Predict Air Quality – continued
19 Optimizers
20 Neural Networks For Classification
21 Classification To Categorize Salary Categories
22 Classification To Categorize Salary Categories – continued

Convolutional Neural Networks In PyTorch
23 Viewing An Image
24 Convolution
25 Pooling
26 CNN Architectures
27 Batch Normalization
28 Neural Networks To Classify House Numbers
29 Neural Networks To Classify House Numbers – continued

Recurrent Neural Networks In PyTorch
30 Recurrent Neurons
31 Layers In An RNN
32 Long Short Term Memory
33 Language Prediction Using RNNs
34 Recurrent Neural Networks To Predict Languages Associated With Names
35 Confusion Matrix
36 Confusion Matrix For Classification

Transfer Learning And Pre-trained Models
37 Transfer Learning
38 Resnet-18 Model To Classify Fruits
39 Resnet-18 Model To Classify Fruits – continued
40 Summary