Machine Learning: Predict Numbers from Handwritten Digits using a Neural Network, Keras, and R

Оценки: 53
от партнера
Coursera Project Network
4,315 уже зарегистрированы
В этом Проект с консультациями вы:

Train and Test a Neural Network Model to read hand written numbers and return the digit.

Practice using One Hot Encoding to build a classifier.

Practice evaluating model performance.

Clock2 Hours
IntermediateУчащийся среднего уровня
CloudЗагрузка не требуется
VideoВидео на разделенном экране
Comment DotsАнглийский
LaptopТолько для ПК

In this 1-hour long project-based course, you will learn how to build a Neural Network Model using Keras and the MNIST Data Set. By the end of the course you will have built a model that will recognize the digits of hand written numbers. You will also be exposed to One Hot Encoding, Neural Network Architecture, Loss Optimizers and Testing of the Model's performance. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Навыки, которые вы получите

Artificial Neural NetworkAnalyticsMachine Learning

Будете учиться пошагово

На видео, которое откроется рядом с рабочей областью, преподаватель объяснит эти шаги:

  1. Task 1: In this task the Learner will be introduced to the Course Objectives, which is to how to execute a Neural Network on the MNIST Data Set. There will also be a short discussion about the Interface, loading packages, and an Instructor Bio.

  2. Task 2: The Learners will see what a Tensor looks like and then apply that knowledge to 60,000 hand written digits using Keras array_reshape() function.

  3. Task 3: The Learner will then create a classifier using one hot encoding.

  4. Task 4: The Learner will then build out the architecture for the Neural Network. Rectified Linear Unit ("RELU") and SoftMax will be used.

  5. Task 5: The Learner will then build out a loss optimizer function using cross_entropy.

  6. Task 6: The Learner will test to see how the model performed using a Confusion Matrix.Task 3: The Learner will get experience creating Testing and Training Data Sets. There are multiple ways to do this and the Instructor will go over two of them in this Task.

Как устроены проекты с консультациями

Ваше рабочее пространство — это облачный рабочий стол в браузере. Ничего не нужно загружать.

На разделенном экране видео преподаватель предоставляет пошаговые

Часто задаваемые вопросы

Часто задаваемые вопросы

Остались вопросы? Посетите Центр поддержки учащихся.