AI Short Courses, New From Udacity
Written by Sue Gee   
Friday, 02 June 2023

Udacity has announced a new course every day for the last fortnight. Each one provides you with job ready skills in less than a month and for a limited time you can take advantage of a 50% discount. 

The premise behind the fourteen courses that Udacity has just launched are that you can learn practical technical skills in less than a month. Between them they cover a wide range of topics, including Data Science, AI, Programming, and Cybersecurity.


My three picks today are all AI-related so if you want to know about the other eleven take a look at the full list of Udacity Short Online Courses that share the enrollment date of June 7th and which are being introduced for half the regular cost, $200 per month instead of $399.

I make no apology for choosing courses related to AI. While some are alarmed at the pace of development towards efficient and effective artificial intelligence embracing it and understanding how it works - and how we can both use it to our advantage and keep it under control - seems a more rational approach. For some, an even better idea is to be on the inside and look for a career at the forefront of AI.

Udacity's courses are co-created with tech companies and are taught by instructors who are experts. Learners receive support from technical mentors and receive personalized project feedback with line-by-line code review. Udacity claims:

Our learn-by-doing approach incorporates projects based on real-world scenarios. They aren’t just multiple choice questions graded by bots—they are open-ended and require critical thinking. Just like the workplace.

Although these new courses are designed to be completed within one month, they are still project-based and highly practical. The Course Project is listed first in the outlines below, followed by the lessons that impart the required knowledge.

Building Generative Adversarial Networks

At Advanced level, in this course you'll learn how to build and train different generative adversarial network architectures to generate new images. Its prerequisites include knowing about  Convolutional Neural Networks (CNNs), intermediate Python proficiency and experience with PyTorch.

Course Project: Face Generation

Build and train a custom GAN architecture on the CelebA dataset, leveraging the different skills learned during the course. Build a custom GAN architecture, including generator and discriminator. Experiment with the different loss functions discovered during the course, such as the Binary Cross Entropy loss or the Wasserstein loss. Finally, you’ll utilize some of the methods learned to stabilize training, such as label smoothing.

  1. Generative Adversarial Networks

    Build generator and discriminator using fully connected layers. Implement loss functions and train a custom GAN on the MNIST dataset.

  2. Training a Deep Convolutional GANs

    Build generator and discriminator using convolutions, batch normalization, and fully connected layers. Train a DCGAN model on the CIFAR10 dataset and implement evaluation metrics and evaluate generated samples.

  3. Image to Image Translation

    Implement unpaired data loader. Build the CycleGAN generator using residual connection and an encoder-decoder structure. Train a CycleGAN model on the summer2winter Yosemite dataset.

  4. Modern GANs

    Implement Wasserstein loss and gradient penalties and build the ProGAN generator. Implement StyleGAN components (adaptive instance normalization).

Introduction to Deep Learning

At Intermediate level, this course provides a deep dive into the fundamental theoretical and practical topics related to deep learning. Its prerequisites are intermediate Python skills and experience with Jupyter notebooks, Pandas and NumPy and Machine Learning Frameworks.

Course Project: Developing a Handwritten Digits Classifier with PyTorch

Develop a handwritten digit recognition system in PyTorch. Then, use data preprocessing skills to load data appropriately for use in models. Develop a neural network using PyTorch and write a training loop that trains the model with the loaded data. Lastly, apply advanced training techniques to improve accuracy on the test set.

  1. Deep Learning

    Explain the difference between artificial intelligence, machine learning, and deep learning. Recognize the power of deep learning by reviewing popular examples of deep learning applications

  2. Minimizing the Error Function with Gradient Descent

    Use PyTorch to preprocess data and use maximum likelihood, cross-entropy, and probability to measure model performance. Apply gradient descent to minimize error. Implement a backpropagation algorithm and identify key components of perceptrons.

  3. Introduction to Neural Networks

    Explain essential concepts in neural networks and design neural network architectures. Distinguish between problems based on the objective of the model. Implement appropriate architectures for model objectives

  4. Training Neural Networks

    Define a loss function and optimization method to train a neural network. Distinguish between overfitting and underfitting, and identify the causes of each. Optimize the training process using early stopping, regularication, dropout, learning rate decay, and momentum. Distinguish between batch and stochastic gradient descent and build a neural network with PyTorch and run data through it. Test and validate a trained network to ensure it generalizes.

Advanced Computer Vision and Deep Learning

In this course you'll discover how to combine CNN and RNN networks to build an automatic image captioning application. Learners should have knowledge of probability basics, deep learning frameworks, intermediate Python, neural network basics, and object-oriented programming basics.

Course Project: Image Captioning

Combine CNN and RNN knowledge to build a deep learning model that produces captions given an input image. Image captioning requires that learners create a complex deep learning model with two components: a CNN that transforms an input image into a set of features, and an RNN that turns those features into rich, descriptive language. In this project, you will implement these cutting-edge deep learning architectures.

  1. Advanced CNN Architectures

    Describe advances in CNN architectures. Understand region-based CNN’s, Fast R-CNN, and Faster-R-CNN, which allow for fast, localized object recognition in images.

  2. YOLO

    Understand grid, sliding windows, and bounding boxes in object detection. Implement YOLO, a real-time object detection algorithm.

  3. RNN’s

    Understand how recurrent neural networks learn from ordered sequences of data. Identify RNN applications in deep learning. Understand how feedforward and backpropagation through time work as well as RNN unfolded model.

  4. Long Short-Term Memory Networks (LSTMs)

    Explore how memory can be incorporated into a deep learning model and implement long short-term memory networks.

  5. Hyperparameters

    Refresh important hyperparameters such as learning rate, epochs, and layer and understand hyperparameters in RNN.

  6. Optional: Attention Mechanisms

    Understand how attention allows models to focus on a specific piece of input data. Describe where attention is useful in natural language and computer vision applications. Describe attention and its encoder and decoder that empower applications like text translation. Understand basic attention methods like additive attention, Bahdanau and Luong attention

  7. Image Captioning
    Understand image captioning and tokenize captions and words. Combine CNNs and RNNs to build a complex captioning model.

If you don't already have all the prerequisites you need for these courses the Udacity GPT, the recently introduced chatbot, can provide recommendations.



More Information

Udacity Short Online Courses

Building Generative Adversarial Networks

Introduction to Deep Learning

Advanced Computer Vision and Deep Learning

Related Articles

Google Boosts Opportunities For Job Seekers

Grow With Google

Data Scientist or Data Engineer? Choose Your Path On Udacity

Udacity Data Science Nanodegrees Restarting 

Data Scientists Salary Data 

Data Scientist Best Paying Entry-Level Job Says Glassdoor 

It Pays To Get Certification

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.


Android Studio Jellyfish Ready To Use

Well, as ready as any of the recent Android Studio's have been. This one boasts an AI assistant called Gemini - shame Android Studio isn't as fast to implement as Gemini is to suggest.

At What Age Do Programmers Write Languages?

This is just one of many question that can be answered by reference to PLDB, the programming language database devised and maintained by Breck Yunits, himself the author of Scroll, an o [ ... ]

More News

raspberry pi books



or email your comment to:


Last Updated ( Friday, 02 June 2023 )