Hyperparameter Tuning with Keras Tuner

4.7
별점
36개의 평가
제공자:
Coursera Project Network
학습자는 이 무료 안내 프로젝트에서 다음을 수행하게 됩니다.

Create and run hyperparameter tuning experiments using Keras Tuner

Create and use Custom Keras Tuners

인터뷰에서 이 안내형 체험 보여주기

Clock2 hours
Intermediate중급
Cloud다운로드 필요 없음
Video분할 화면 동영상
Comment Dots영어
Laptop데스크톱 전용

In this 2-hour long guided project, we will use Keras Tuner to find optimal hyperparamters for a Keras model. Keras Tuner is an open source package for Keras which can help machine learning practitioners automate Hyperparameter tuning tasks for their Keras models. The concepts learned in this project will apply across a variety of model architectures and problem scenarios. Please note that we are going to learn to use Keras Tuner for hyperparameter tuning, and are not going to implement the tuning algorithms ourselves. At the time of recording this project, Keras Tuner has a few tuning algorithms including Random Search, Bayesian Optimization and HyperBand. In order to complete this project successfully, you will need prior programming experience in Python. This is a practical, hands on guided project for learners who already have theoretical understanding of Neural Networks, and optimization algorithms like gradient descent but want to understand how to use Keras Tuner to start optimizing hyperparameters for training their Keras models. You should also be familiar with the Keras API. 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.

요구 사항

Prior programming experience in Python. Conceptual understanding of Neural Networks. Prior experience with TensorFlow and Keras.

개발할 기술

  • Deep Learning
  • Machine Learning
  • Hyperparameter Optimization
  • hyperparameter tuning
  • keras

단계별 학습

작업 영역이 있는 분할 화면으로 재생되는 동영상에서 강사는 다음을 단계별로 안내합니다.

  1. Introduction

  2. Installing Keras Tuner and Downloading the Data

  3. Creating the Model

  4. Hyperparameters

  5. Keras Tuner

  6. Training Results

안내형 프로젝트 진행 방식

작업 영역은 브라우저에 바로 로드되는 클라우드 데스크톱으로, 다운로드할 필요가 없습니다.

분할 화면 동영상에서 강사가 프로젝트를 단계별로 안내해 줍니다.

자주 묻는 질문

자주 묻는 질문

궁금한 점이 더 있으신가요? 학습자 도움말 센터를 방문해 보세요.