logo-mooc
search-iconsearch-icon
menu-whitemenu-blue
GRATIS
Inicio / Buscador / Ciencias de la Computación / Aprendizaje Supervisado
Yale University vía Coursera
GRATIS

Introduction to Deep Learning & Neural Networks with Keras

  • money

    Cursos gratis (Auditar)

    question-mark
  • earth

    Inglés

  • folder

    Siempre Abierto

  • certificate

    Guía de Registro en Coursera

    arrow
VER CURSO arrow
Acerca de este curso

  • Introduction to Neural Networks and Deep Learning
    • In this module, you will learn about exciting applications of deep learning and why now is the perfect time to learn deep learning. You will also learn about neural networks and how most of the deep learning algorithms are inspired by the way our brain functions and the neurons process data. Finally, you will learn about how neural networks feed data forward through the network.
  • Artificial Neural Networks
    • In this module, you will learn about the gradient descent algorithm and how variables are optimized with respect to a defined function. You will also learn about backpropagation and how neural networks learn and update their weights and biases. Futhermore, you will learn about the vanishing gradient problem. Finally, you will learn about activation functions.
  • Keras and Deep Learning Libraries
    • In this module, you will learn about the diifferent deep learning libraries namely, Keras, PyTorch, and TensorFlow. You will also learn how to build regression and classification models using the Keras library.
  • Deep Learning Models
    • In this module, you will learn about the difference between the shallow and deep neural networks. You will also learn about convolutional networks and how to build them using the Keras library. Finally, you will also learn about recurrent neural networks and autoencoders.
  • Course Project
    • In this module, you will conclude the course by working on a final assignment where you will use the Keras library to build a regression model and experiment with the depth and the width of the model.