Chevron Left
返回到 Introduction to Deep Learning & Neural Networks with Keras

学生对 IBM 提供的 Introduction to Deep Learning & Neural Networks with Keras 的评价和反馈

4.7
星
1,986 个评分

课程概述

This course introduces deep learning and neural networks with the Keras library. In this course, you’ll be equipped with foundational knowledge and practical skills to build and evaluate deep learning models. You’ll begin this course by gaining foundational knowledge of neural networks, including forward and backpropagation, gradient descent, and activation functions. You will explore the challenges of deep network training, such as the vanishing gradient problem, and learn how to overcome them using techniques like careful activation function selection. The hands-on labs in this course allow you to build regression and classification models, dive into advanced architectures, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and autoencoders, and utilize pretrained models for enhanced performance. The course culminates in a final project where you’ll apply what you’ve learned to create a model that classifies images and generates captions. By the end of the course, you’ll be able to design, implement, and evaluate a variety of deep learning models and be prepared to take your next steps in the field of machine learning....

热门审阅

SS

Jun 29, 2020

Such a wonderful and high tech course in the world and it is provided by ibm and coursera.Thank you ibm and coursera for such a opportunity.I'm glad and proud to be a part of this organization.

MP

Jun 30, 2022

Excellent introduction to the mechanics of Neural Networks in general, and the Keras application specifically. Alec is an outstanding teacher, I always appreciate his knowledge and enthusiasm.

筛选依据：

276 - Introduction to Deep Learning & Neural Networks with Keras 的 300 个评论（共 381 个）

创建者 Ridha O

•

Feb 11, 2022

good one

创建者 Simha C

•

Aug 26, 2024

Awesome

创建者 SURYA B

•

May 7, 2025

useful

创建者 José M

•

Mar 27, 2023

Good!!

创建者 Dastur K

•

Jul 12, 2025

good!

创建者 parisa z

•

Nov 9, 2022

great

创建者 Francisco M L L

•

Aug 8, 2022

great

创建者 said f

•

Mar 29, 2020

super

创建者 Jatin 0

•

Aug 31, 2025

good

创建者 Rakshita

•

Aug 30, 2025

good

创建者 Rasim A

•

Apr 29, 2025

Good

创建者 prakhar

•

Apr 25, 2025

good

创建者 Nurzat D

•

Apr 19, 2025

Good

创建者 Nithya P V 2

•

Mar 28, 2025

dfdf

创建者 Ahmed E

•

Aug 15, 2024

good

创建者 Sardor B

•

May 22, 2024

good

创建者 Astitva S

•

Mar 18, 2024

good

创建者 01fe21bec413

•

Mar 16, 2024

Good

创建者 mezmur w

•

Mar 5, 2024

best

创建者 afra a a

•

Dec 21, 2023

good

创建者 Muhammad M T

•

Mar 22, 2023

good

创建者 Krishna H

•

Apr 28, 2020

good

创建者 Khánh N

•

May 24, 2025

oke

创建者 harkirat s s

•

Sep 7, 2025

ok

创建者 Gorana B

•

Jul 22, 2024

It is short and comprehensive introduction. It could have had a dedicated module on evaluation of the models, with visualizations of target vs predictions and losses. From evaluation of peer-graded assignments I get the impression this is not well understood (ways to do it, meaning of values vs training and epochs). On the other hand peer graded assignment should be more challenging than what is shown throughout the course. So maybe it is enough what was shown throughput the course, as current assignment is a bit more challenging. Otherwise students end up copy pasting materials (which I have seen too often). My problem is more on the concept of evaluation of the assignment and points to be given. Scale is too coarse. And submission request should be less loose - jupyter notebook or python files, not html or pdf files. And some system that is automatically checking for similarities among student's assignments prior to submission would be good to have.