About this Course

55,276 recent views

Learner Career Outcomes

23%

started a new career after completing these courses

38%

got a tangible career benefit from this course

57%

got a pay increase or promotion

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Advanced Level

Approx. 18 hours to complete

Suggested: 4 weeks of study, 4-6 hours/week...

English

Subtitles: English

Skills you will gain

Machine LearningDeep LearningLong Short-Term Memory (ISTM)Apache Spark

Learner Career Outcomes

23%

started a new career after completing these courses

38%

got a tangible career benefit from this course

57%

got a pay increase or promotion

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Advanced Level

Approx. 18 hours to complete

Suggested: 4 weeks of study, 4-6 hours/week...

English

Subtitles: English

Instructors

Instructor rating4.25/5 (19 Ratings)Info
Image of instructor, Romeo Kienzler

Romeo Kienzler 

Chief Data Scientist, Course Lead
IBM Watson IoT
53,524 Learners
5 Courses
Image of instructor, Niketan Pansare

Niketan Pansare 

Senior Software Engineer
IBM Research
30,052 Learners
1 Course
Image of instructor, Tom Hanlon

Tom Hanlon 

Training Director
Skymind
30,052 Learners
1 Course
Image of instructor, Max Pumperla

Max Pumperla 

Deep Learning Engineer
30,052 Learners
1 Course
Image of instructor, Ilja Rasin

Ilja Rasin 

Data Scientist
IBM Watson Health
30,052 Learners
1 Course

Offered by

IBM logo

IBM

Syllabus - What you will learn from this course

Content RatingThumbs Up84%(2,206 ratings)Info
Week
1

Week 1

5 hours to complete

Introduction to deep learning

5 hours to complete
17 videos (Total 65 min), 6 readings, 2 quizzes
17 videos
Introduction - Romeo Kienzler30s
Introduction - Ilja Rasin1m
Introduction - Niketan Pansare30s
Introduction - Tom Hanlon1m
Course Logistics1m
Cloud Architectures for AI and DeepLearning4m
Linear algebra6m
Deep feed forward neural networks12m
Convolutional Neural Networks4m
Recurrent neural networks1m
LSTMs3m
Auto encoders and representation learning2m
Methods for neural network training8m
Gradient Descent Updater Strategies6m
How to choose the correct activation function3m
The bias-variance tradeoff in deep learning3m
6 readings
IBM Digital Badge10m
Video summary on environment setup10m
Where to get all the code and slides for download?10m
IMPORTANT: How to submit your programming assignments10m
Introduction to ApacheSpark10m
Link to Github10m
1 practice exercise
DeepLearning Fundamentals14m
Week
2

Week 2

7 hours to complete

DeepLearning Frameworks

7 hours to complete
24 videos (Total 168 min), 1 reading, 5 quizzes
24 videos
Neural Network Debugging with TensorBoard7m
Automatic Differentiation2m
Introduction video44s
Keras overview5m
Sequential models in keras6m
Feed forward networks7m
Recurrent neural networks9m
Beyond sequential models: the functional API3m
Saving and loading models2m
What is SystemML (1/2) ?3m
What is SystemML (2/2) ?6m
Demo - How to use Apache SystemML on IBM DSX (1/3)4m
Demo - How to use Apache SystemML on IBM DSX (2/3)3m
Demo - How to use Apache SystemML on IBM DSX (3/3)8m
Introduction to DeepLearning4J12m
Demo: Running Java in Data Science Experience8m
DL4J Neural Network Code Example, Mnist Classifier14m
PyTorch Installation2m
PyTorch Packages2m
Tensor Creation and Visualization of Higher Dimensional Tensors6m
Math Computation and Reshape7m
Computation Graph, CUDA17m
Linear Model17m
1 reading
Link to files in Github10m
4 practice exercises
TensorFlow12m
Apache SystemML12m
DL4J Fundamentals12m
PyTorch Introduction12m
Week
3

Week 3

6 hours to complete

DeepLearning Applications

6 hours to complete
18 videos (Total 115 min), 1 reading, 5 quizzes
18 videos
How to implement an anomaly detector (1/2)11m
How to implement an anomaly detector (2/2)2m
How to deploy a real-time anomaly detector2m
Introduction to Time Series Forecasting4m
Stateful vs. Stateless LSTMs6m
Batch Size5m
Number of Time Steps, Epochs, Training and Validation8m
Trainin Set Size4m
Input and Output Data Construction7m
Designing the LSTM network in Keras10m
Anatomy of a LSTM Node12m
Number of Parameters7m
Training and loading a saved model4m
Classifying the MNIST dataset with Convolutional Neural Networks5m
Image classification with Imagenet and Resnet503m
Autoencoder - understanding Word2Vec8m
Text Classification with Word Embeddings4m
1 reading
Generative Adversarial Networks (GANs) (optional)10m
4 practice exercises
Anomaly Detection12m
Sequence Classification with Keras LSTM Network12m
Image Classification6m
NLP6m
Week
4

Week 4

4 hours to complete

Scaling and Deployment

4 hours to complete
5 videos (Total 40 min), 3 readings, 2 quizzes
5 videos
Creating and Scaling a Keras Model in ApacheSpark using DL4J14m
Creating and Scaling a Keras Model in ApacheSpark using DL4J (Demo)16m
Computer Vision with IBM Watson Visual Recognition2m
Text Classification with IBM Watson Natural Language Classifier1m
3 readings
Parallel Neural Network Training10m
Scale a Keras Model with IBM Watson Machine Learning10m
Link to Github10m
1 practice exercise
Run a Notebook using Keras and DL4J6m
4.5
97 ReviewsChevron Right

Top reviews from Applied AI with DeepLearning

By RCApr 26th 2018

It was really great learning with coursera and I loved the course. The way faculty teaches here is just awesome as they are very much clear and helped a lot while learning this coursea

By BSAug 8th 2019

Gave a good hands-on with IBM Watson studio notebooks. Also a good overview of LSTM's, Keras, Predictive maintenance. Good stuff, keep it going

About the Advanced Data Science with IBM Specialization

As a coursera certified specialization completer you will have a proven deep understanding on massive parallel data processing, data exploration and visualization, and advanced machine learning & deep learning. You'll understand the mathematical foundations behind all machine learning & deep learning algorithms. You can apply knowledge in practical use cases, justify architectural decisions, understand the characteristics of different algorithms, frameworks & technologies & how they impact model performance & scalability. If you choose to take this specialization and earn the Coursera specialization certificate, you will also earn an IBM digital badge. To find out more about IBM digital badges follow the link ibm.biz/badging....
Advanced Data Science with IBM

Frequently Asked Questions

  • Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.

  • When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.

  • The IBM Watson IoT Certified Data Scientist degree is a Coursera specialization IBM is currently creating. This course is one part of 3-4 courses coming up the next couple of months

    Currently only this and another course exist. The other one is the following:

    https://www.coursera.org/learn/exploring-visualizing-iot-data

    The course above will be modified and renamed to "Fundamentals of Applied DataScience" - but if you pass it today, it counts towards the certificate as well

More questions? Visit the Learner Help Center.