Deep Learning with Pytorch

Name: Deep Learning with Pytorch
Rating: 4.4 (15 reviews)

Learn how to implement a neural network using Pytorch

Created byLeo Bravo

Last updated 4/2021

English

English [Auto],

What you'll learn

Learn what is Deep Learning
Learn what is a Neural Network
Learn real world use cases of Deep Learning
Learn the mathematics behind the neural networks
Learn different types of Neural Networks
Learn how to train a neural network
Learn how to use Pytorch framework to build a Neural Network model
Learn how to use Python to build a Deep Learning project
Learn how to use Jupyter notebook to build a Deep Learning project
Learn how to create and train a neural network model with Pytorch
Learn how to analize a neural network training and measure the perfomance while training
Learn how to evaluate a neural network model and get metrics to analize general perfomance
Learn how to apply changes and exploration analisis in order to improve the neural network model

Course content

2 sections • 17 lectures • 3h 41m total length

Overview of Deep Learning6:08
What is a Neural Network?11:15
Use cases of Neural Networks3:59
Explore the use cases of deep learning, including image segmentation for self-driving cars and neural network stock price predictions from time-series data.
Mathematical view of Neural Networks12:54
Explore the mathematical view of neural networks using a multilayer perceptron, detailing weighted connections, biases, and nonlinear activation to form complex function mappings.
Type of Neural Networks models7:16
Explore neural network types, including fully connected model, convolutional networks with filters and pooling, and recurrent networks for time series, and see how data type guides architecture and model choice.
Mathematical view of training a Neural Network18:14
Practical view of training a Neural Network15:47

Practical example presentation7:50
Classify iris species (setosa, versicolor, virginica) with a 4-feature dataset (sepal length, sepal width, petal length, petal width) using a two-layer feed-forward neural network.
Load dataset10:27
We are using the Iris Dataset, you can download it freely here:

https://archive.ics.uci.edu/ml/datasets/iris

We are using Jupyter Notebook to write and run the code, but you can use the tool you want!
Display and analyze data10:13
Get data to train model15:25
Extract and transform data to train a neural network that classifies species, preparing features X and labels y by dropping the species column and converting to tensors for PyTorch.
Create Neural Network model22:36
Create a neural network model in PyTorch by defining a class with fully connected layers, an activation function, and a three-class output, using four input features and twenty-five hidden units.
Define methods to train model6:33
Define the training method by selecting a cost function for multi-class classification, such as cross-entropy loss, and configure an optimizer to update model parameters.
Train model: train dataset20:22
Train the model across epochs by computing predictions, calculating loss, and updating parameters via backpropagation with an optimizer, while plotting the train loss.
Train model: validation dataset19:41
Train and evaluate the model using a validation dataset by computing predictions, loss, and accuracy across epochs, then plot validation loss and accuracy to assess training progress.
Analize model on test dataset and metrics24:58
Evaluate the model on the unseen test dataset to compute metrics such as accuracy, precision, recall, and F1 score, using confusion matrices and classification reports to assess generalization.
Practical advices about training7:37

Requirements

Basic Python knowledge is required
No previous knowledge in Deep Learning is required
No previous knowledge in Machine Learning is required
No previous knowledge in Pytorch is required

Description

In this course, you are going to learn what is and how to implement a Neural Network model. To do this, you will use the library Pytorch using Python programming language, a tool that allows you to easily build a neural network model.

In the first part of the course, you will learn the basic about the theory of Deep Learning and then we will go deeper in the mathematics behind neural networks so that you can understand how these models works, how they are trained and evaluated and with this knowledge, you can change stuff in order to improve your own models.

After the theoretical part, you will build a practical project in which you will build a neural network model to classify plants into different species. To do this you will use Pytorch, a library that allows you to create and train a neural network model using Python. First, you will create the model using a specific architecture, and then you will train the model by applying all the concepts you learned in the theoretical part. After training, you will get metrics that will allow you to analyze and evaluate how good is your model. Based on the results, you will learn how to implement changes into your project so that you can learn how to explore different options in order to improve the model perfomance.

You don't need previous knowledge on Deep Learning or Pytorch, because you will learn the basics you need in order to build a deep learning project using this technology.

So, get started building deep learning projects with this very practical course.

Who this course is for:

Anyone who wants to learn about how to implement a neural network using Python and Pytorch
Anyone who wants to learn about how a Deep Learning project is developed

Deep Learning with Pytorch

What you'll learn

Explore related topics

Course content

What is a neural network?7 lectures • 1hr 16min

Neural Networks with Pytorch10 lectures • 2hr 26min

Requirements

Description

Who this course is for: