Ir al contenido principal

Deep Learning with Python and PyTorch

Ofrecido por IBM
Intermediate
Ver requisitos
2–4 horas
por semana, durante 6 semanas
Gratis

$99 USD para exámenes y tareas con calificación, más un certificado

Learn how to use Python and its popular libraries such as NumPy and Pandas, as well as the PyTorch Deep Learning library. You'll then apply them to build Neural Networks and Deep Learning models.

Antes de comenzar

  • Python & Jupyter notebooks
  • Machine Learning concepts
  • Deep Learning concepts
Inicio del curso: Oct 1, 2018
Finalización del curso: Nov 23, 2020

Lo que aprenderás

  • Explain and apply knowledge of Deep Neural Networks and related machine learning methods;
  • Know how to use Python, and Python libraries such as Numpy and Pandas along with the PyTorch library for Deep Learning applications;
  • Build Deep Neural Networks using PyTorch.
Module 1 – Introduction to Pytorch
  • What’s Deep Learning and why Pytorch
  • 1-D Tensors and useful Pytoch Functions
  • 2-D Tensors and useful functions
  • Derivatives and Graphs in Pytorch
  • Data Loader
 
Module 2 – Linear Regression
  • Prediction 1D regression
  • Training 1D regression
  • Stochastic gradient descent, mini-batch gradient descent
  • Train, test, split and early stopping
  • Pytorch way
  • Multiple Linear Regression

Module 3 - Classification
  • Logistic Regression
  • Training Logistic Regressions Part 1
  • Training Logistic Regressions Part 2
  • Softmax Regression
 
Module 4 - Neural Networks
  • Introduction to Networks
  • Network Shape Depth vs Width
  • Back Propagation
  • Activation functions

Module 5 - Deep Networks
  • Dropout
  • Initialization
  • Batch normalization
  • Other optimization methods

Module 6 - Computer Vision Networks
  • Convolution
  • Max Polling
  • Convolutional Networks
  • Pre-trained Networks

Información general

The course will teach you how to develop Deep Learning models using Pytorch while providing the necessary deep-learning background.

We'll start off with PyTorch's tensors and its Automatic Differentiation package. Then we'll cover different Deep Learning models in each section, beginning with fundamentals such as Linear Regression and logistic/softmax regression.
We'll then move on to Feedforward deep neural networks, the role of different activation functions, normalization and dropout layers.

In the final part of the course, we'll focus on Convolutional Neural Networks and Transfer Learning (pre-trained models). Several other Deep Learning methods will also be covered.

Conoce a tus instructores

Joseph Santarcangelo
PhD., Data Scientist
IBM

¿Quién puede hacer este curso?

Lamentablemente, las personas de uno o más de los siguientes países o regiones no podrán registrarse para este curso: Irán, Cuba y la región de Crimea en Ucrania. Si bien edX consiguió licencias de la Oficina de Control de Activos Extranjeros de los EE. UU. (U.S. Office of Foreign Assets Control, OFAC) para ofrecer nuestros cursos a personas en estos países y regiones, las licencias que hemos recibido no son lo suficientemente amplias como para permitirnos dictar este curso en todas las ubicaciones. edX lamenta profundamente que las sanciones estadounidenses impidan que ofrezcamos todos nuestros cursos a cualquier persona, sin importar dónde viva.

Ver cursos
Este curso forma parte de:

Obtén un Professional Certificate de de 2 a 4 meses si tomas un curso a la vez.

Ver el programa
  1. 10–20 horas de trabajo

    New to deep learning? Start with this course, that will not only introduce you to the field of deep learning but give you the opportunity to build your first deep learning model using the popular Keras library.

  2. Deep Learning with Python and PyTorch
  3. 10–20 horas de trabajo

    Much of the world's data is unstructured. Think images, sound, and textual data. Learn how to apply Deep Learning with TensorFlow to this type of data to solve real-world problems.

  4. 10–20 horas de trabajo

    Training complex deep learning models with large datasets takes a long time. In this course, you will learn how to use accelerated GPU hardware to overcome the scalability problem in deep learning.

  5. 10–20 horas de trabajo

    In this capstone project, you'll use either Keras or PyTorch to develop, train, and test a Deep Learning model. Load and preprocess data for a real problem, build the model and then validate it.

Comienza con análisis de datos y estadísticas

Explorar 200 cursos de análisis de datos y estadísticas
Del total de los estudiantes de edX:
El 73% tiene empleo
Del total de los estudiantes de edX:
El 45% tiene hijos
Según los resultados de encuestas internas
357,074 personas están aprendiendo hoy en edX