← Back

Introduction to Deep Learning & Neural Networks with Keras

IBM · View on Coursera ↗

Or see the score while you browse.

Taught by Alex Aklson

Data ScienceComputer Science

Coursera
4.7
headline rating
↓
0.9
gap
Starisk
3.8
Padded

About the course

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.

Read more

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.

The dissent

The most-upvoted critical review (8 votes, 2.0★).

“2) It was IMPOSSIBLE for me to get feedback from the Staff at any question. I ended up solving the issues by my own and through try and error, which is fine from a self-study approach, but when it comes to technical issues, it can get quite complicated...”

2.0 / 5

Read the full review on Coursera ↗

Coursera's 4.7 comes from 2,151 ratings. Of those, 2.1% are 1–2★.

Starisk reads the reviews learners voted most helpful, and weights each by the square root of its votes: a review with 80 upvotes counts about five times one with 2. Unvoted reviews are not skipped out of laziness — by this model they carry no evidence that other students endorsed them.

That measures what the most-endorsed reviews say, not “true quality.” The rating distribution above is the whole population, so you can see the sample next to it.

Reviews read on 9 Nov 2026.Read them on Coursera ↗