list 16 sequencias
assignment Nível: Introdutório
chat_bubble_outline Idioma: Inglês
card_giftcard 896 pontos
Avaliações
-
starstarstarstarstar

Informações principais

credit_card Free accesso
verified_user Certificado gratuito
timer 112 total de horas

Sobre o conteúdo

Learn about artificial neural networks and how they're being used for machine learning, as applied to speech and object recognition, image segmentation, modeling language and human motion, etc. We'll emphasize both the basic algorithms and the practical tricks needed to get them to work well. This course contains the same content presented on Coursera beginning in 2013. It is not a continuation or update of the original course. It has been adapted for the new platform. Please be advised that the course is suited for an intermediate level learner - comfortable with calculus and with experience programming (Python).

more_horiz Ler mais
more_horiz Ler menos
dns

Programa de estudos

  • Week 1 - Introduction
    Introduction to the course - machine learning and neural nets
  • Week 2 - The Perceptron learning procedure
    An overview of the main types of neural network architecture
  • Week 3 - The backpropagation learning proccedure
    Learning the weights of a linear neuron
  • Week 4 - Learning feature vectors for words
    Learning to predict the next word
  • Week 5 - Object recognition with neural nets
    In this module we look at why object recognition is difficult.
  • Week 6 - Optimization: How to make the learning go faster
    We delve into mini-batch gradient descent as well as discuss adaptive learning rates.
  • Week 7 - Recurrent neural networks
    This module explores training recurrent neural networks
  • Week 8 - More recurrent neural networks
    We continue our look at recurrent neural networks
  • Week 9 - Ways to make neural networks generalize better
    We discuss strategies to make neural networks generalize better
  • Week 10 - Combining multiple neural networks to improve generalization
    This module we look at why it helps to combine multiple neural networks to improve generalization
  • Week 11 - Hopfield nets and Boltzmann machines
     
  • Week 12 - Restricted Boltzmann machines (RBMs)
    This module deals with Boltzmann machine learning
  • Week 13 - Stacking RBMs to make Deep Belief Nets
     
  • Week 14 - Deep neural nets with generative pre-training
     
  • Week 15 - Modeling hierarchical structure with neural nets
     
  • Week 16 - Recent applications of deep neural nets
     
record_voice_over

Instrutores

  • Geoffrey Hinton, Professor
    Department of Computer Science
store

Criador do conteúdo

University of Toronto
Established in 1827, the University of Toronto has one of the strongest research and teaching faculties in North America, presenting top students at all levels with an intellectual environment unmatched in depth and breadth on any other Canadian campus.
assistant

Plataforma

Coursera

A Coursera é uma empresa digital que oferece um curso on-line massivo e aberto, fundado pelos professores de computação Andrew Ng e Daphne Koller Stanford University, localizado em Mountain View, Califórnia.

O Coursera trabalha com as melhores universidades e organizações para disponibilizar alguns dos seus cursos on-line e oferece cursos em várias disciplinas, incluindo: física, engenharia, humanidades, medicina, biologia, ciências sociais, matemática, negócios, ciência da computação, marketing digital, ciência de dados. e outros assuntos.Cours

Você é o criador deste MOOC?
Qual a sua apinião sobre esse recurso?
Conteúdo
0/5
Platforma
0/5
Didática
0/5