Microsoft's Artificial Intelligence for Beginners
Written by Nikos Vaggalis   
Monday, 22 August 2022

There's a new free, self-paced, online course about Artificial Intelligence from Microsoft's Azure Cloud Advocates. Its 24 lesson curriculum, expected to take 12 weeks to complete, is targeted at those brand new to Artificial Intelligence.

This is a continuation of last year's Microsoft's Machine Learning for Beginners.That course made a clear distinction between Machine Learning and AI - it was about "classic machine learning" and did not concern itself with artificial intelligence. That is the job of its sibling course, AI for Beginners.This separation of topics meant that ML for Beginners was not as complicated as AI for Beginners is, well at the novice level anyway.

Both courses require Python. ML uses Sci-kit and with good reason :

Python certainly is the most popular language of doing ML, mainly due to the number of relevant libraries available. scikit-learn is one of the top Machine Learning libraries alongside PyTorch, NumPy, SciPy, TensorFlow and Theano.

Additionally, scikit-learn is one of the easiest to learn as such perfect for beginning one's ML journey. That doesn't mean that it lacks functionality though; it is perfectly capable of pulling off many ML tasks such as classification, clustering, pre-processing, regression, etc.

AI on the other hand, uses what ML doesn't - that is it demonstrates Neural Networks and Deep Learning with TensorFlow and PyTorch. So at the higher level, the curriculum is comprised of:

  • Different approaches to Artificial Intelligence, including the "good old" symbolic approach with Knowledge Representation and reasoning (GOFAI)

  • Neural Networks and Deep Learning, as said with TensorFlow and PyTorch

  • Neural Architectures for working with images and text

  • Less popular AI approaches, such as Genetic Algorithms and Multi-Agent Systems

 

That overview in detail translates to :

  • Introduction to AI
      Introduction and History of AI
  • Symbolic AI
      Knowledge Representation and Expert Systems
  • Introduction to Neural Networks
      Perceptron
      Multi-Layered Perceptron and Creating our own
  • Framework
      Intro to Frameworks (PyTorch/TensorFlow)
      Computer Vision
      Microsoft Learn Module on Computer Vision
      Intro to Computer Vision. OpenCV
      Convolutional Neural Networks
      Pre-trained Networks and Transfer Learning
      Autoencoders and VAEs
      Generative Adversarial Networks
      Artistic Style Transfer
      Object Detection
      Semantic Segmentation. U-Net
  • Natural Language Processing
      Microsoft Learn Module on Natural Language
      Text Representation. Bow/TF-IDF
      Semantic word embeddings. Word2Vec and GloVe
      Language Modeling. Training your own embeddings
      Recurrent Neural Networks
      Generative Recurrent Networks
      Transformers. BERT.
      Named Entity Recognition
      Large Language Models, Prompt Programming and Few- 
      Shot Tasks
  • Other AI Techniques
      Genetic Algorithms
      Deep Reinforcement Learning
      Multi-Agent Systems
  • AI Ethics
      AI Ethics and Responsible AI
  • Extras
      Multi-Modal Networks, CLIP and VQGAN

Like its ML predecessor, it is carefully planned and well structured. It includes quizzes, doodles, assignments, projects, group discussions and some executable Jupyter Notebooks, which are often specific to the framework (PyTorch or TensorFlow).

And, in my opinion,  it's quite complete and perfectly addressed to CS students as a side-dish to their classes or for those having touched the subject at college and are looking to expand more under the scope of a Masters degree or of finding a job.

Microsoft with its three part series, Data Science, ML and Al, all for beginners, has managed to cover those closely interrelated fields, giving a holistic education to those interested. In the current job landscape these fields could be used in isolation or in combination. The three-part series has every case covered.

And,of course here at I Programmer we have a keen interest in anything to do with Data/ML/AI as well as the topic of Ethics and as such we highlight many relevant educational resources. You'll find some of those at the end of this article.

If until now you were finding it confusing as to how to get started in the science of AI, then confusion begone. AI for beginners is the perfect place to start from.

 

More Information

Microsoft's Artificial Intelligence for Beginners

Related Articles

Microsoft's Data Science for Beginners

Microsoft's Machine Learning for Beginners

Fly Over the Moon With Microsoft And Python

Introduction to Machine Learning with Scikit-Learn

Yann LeCun’s Deep Learning Course Free From NYU

Artificial Intelligence, Machine Learning and Society

Take Stanford's Introduction to Robotics For Free

Triple Treat Machine Learning

Take Stanford's Natural Language Processing with Deep Learning For Free

Ethics of AI - A Course From Finland

Tensorflow 2.0 In 7 Hours

Take Stanford's Natural Language Understanding For Free

Take Google's Machine Learning Crash Course

Program Deep Learning on the GPU with Triton

 

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.

Banner


Google Opensources Privacy Library
08/11/2024

Google is making a new differential privacy library available as open source. PipelineDP4J is a Java-based library that can be used to analyse data sets while preserving privacy.



Remembering Thomas Kurtz, Co-creator of BASIC
15/11/2024

Thomas Eugene Kurtz, the co-founder of the BASIC programming language, has died at the age of 96. BASIC, which was developed for the purpose of education, popularized computer programming making it ac [ ... ]


More News

espbook

 

Comments




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

Last Updated ( Monday, 22 August 2022 )