The fourth and final course of Coursera's TensorFlow Specialization is now available, with  modules on sequences, time series and prediction. Coursera also has two other new Specializations in related areas.

Sequences, Time Series and Prediction completes the TensorFlow in Practice Specialization. This is a four-month program at intermediate level intended for software developers who want to build AI-powered algorithms using TensorFlow, the AI framework originated by Google and now open sourced.

We first reported on this ML (machine learning) Specialization, which is a collaboration between Andrew Ng's company, deeplearning.ai, and Google's TensorFlow team, when the first, introductory, course launched in March, see TensorFlow For Beginners From Coursera. Now that all its courses available the TensorFlow in Practice Specialization has the following learning outcomes:

• Best practices for TensorFlow, a popular open-source machine learning framework to train a neural network for a computer vision applications.
  
  
• Handle real-world image data and explore strategies to prevent overfitting, including augmentation and dropout.
  
  
• Build natural language processing systems using TensorFlow.
  
  
• Apply RNNs, GRUs, and LSTMs as you train them using text repositories.

It consists of the following courses:

1. Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
   
   
2. Convolutional Neural Networks in TensorFlow
   
   
3. Natural Language Processing in TensorFlow
   
   
4. Sequences, Time Series and Prediction

The pre-requisites for this latest and final, module are to have taken the first 3 courses of the TensorFlow Specialization, to be comfortable coding in Python and with high school-level math. it has the following learning outcomes:

• Solve time series and forecasting problems in TensorFlow
  
  
• Prepare data for time series learning using best practices
  
  
• Explore how RNNs and ConvNets can be used for predictions
  
  
• Build a sunspot prediction model using real-world data

If you want to go further with neural networks, Coursera's  Deep Learning Specialization, also from deeplearning.ai, comprises five courses, between 2 and 4 weeks each (77 hours in total) at intermediate to advanced level. If you need more grounding in Machine Learning as preparation, Andrew Ng's popular Machine Learning course is still available as a free, standalone course.

Coursera has recently added two other Specializations in the closely related areas of artificial intelligence and reinforcement learning.

Applied AI: Artificial Intelligence with IBM Watson Specialization is offered by IBM and consists of six courses, each of 4-5 weeks, at beginner level. Its blurb states:

Rather than create complex AI algorithms and interfaces from scratch, learners will use IBM Watson AI services and APIs to create smart applications with minimal coding. By the end of this Specialization, learners will complete several projects that showcase proficiency in applied AI.

Reinforcement Learning Specialization comes from the University of Alberta and consists of four courses, each of 4-5 weeks, at intermediate level. Its learning outcomes are:

• Build a Reinforcement Learning system for sequential decision making.
  
  
• Understand the space of RL algorithms (Temporal- Difference learning, Monte Carlo, Sarsa, Q-learning, Policy Gradients, Dyna, and more).
  
  
• Understand how to formalize your task as a Reinforcement Learning problem, and how to begin implementing a solution.
  
  
• Understand how RL fits under the broader umbrella of machine learning, and how it complements deep learning, supervised and unsupervised learning

More Information 

Tensorflow in Practice Specialization

Deep Learning Specialization

Applied AI: Artificial Intelligence with IBM Watson Specialization

Reinforcement Learning Specialization

Related Articles

TensorFlow For Beginners From Coursera 

Machine Learning At All Levels On Coursera

Google Provides Free Machine Learning For All

Andrew Ng on Advances In Deep Learning

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info