Generative AI
Text Generation Models: From RNNs to Transformers
How neural text generation moved from recurrent networks and LSTMs through attention to the Transformer, and why recurrence is coming back in new forms.
Cloud · AI · Generative AI
Towards the cloud,
one idea at a time.
Complex tech, broken into fun, digestible bites. Practical guides to AWS, Google Cloud and Azure, and plain-English tours of machine learning and generative AI.
- Articles
- 92
- Series
- 12
- Quiz questions
- 150
Fresh from the blog
Latest reads
Learning paths
Pick a track
Three series that build on each other: start with the cloud, meet the machines that learn, then watch them create.
40 articles
Cloud computing
Fluffy Computing
Foundations of the cloud and hands-on tours of AWS, Google Cloud and Azure — from your first VM to multi-cloud strategy.
- Virtual Machines7
- Diving into Microsoft Azure7
- Exploring Google Cloud Platform (GCP)7
- Getting to Know AWS7
15 articles
AI & machine learning
Artificial Unintelligence
How machines learn: the history of AI, supervised and unsupervised learning, model training and the data behind it all.
- Introduction to Machine Learning and AI9
- Machine Learning Algorithms6
37 articles
Generative AI
Word Up! Bot
Transformers, GANs, VAEs and GPT — what generative AI is, how it works, and how the cloud providers put it to work.
- Introduction to Generative AI30
- Deep Dive into Generative Models7
Quick quiz
Think you know the cloud?
Three quizzes, 150 questions, instant explanations. Your best scores stay on your device.
The 'shared responsibility model' in cloud computing primarily defines the security obligations between:
The shared responsibility model outlines which security tasks are handled by the cloud provider (e.g., security OF the cloud infrastructure) and which are handled by the customer (e.g., security IN the cloud, like data configuration and access management).
Keep exploring
More from the archive
Cloud
Introduction to Containers and Docker
What a container actually is, how it differs from a VM, and how to build, run and ship your first image with Docker before moving it to the cloud.
Generative AI
StyleGAN: Generating High-Resolution Images
How StyleGAN reaches 1024 by 1024 faces: the mapping network, per-layer styles, noise inputs, the truncation trick, and what StyleGAN2, ADA and StyleGAN3 changed.
AI & ML
Random Forest: An Ensemble Learning Method
How random forests turn many unstable decision trees into one reliable model: bagging, random features, out-of-bag scores and working scikit-learn code.
Cloud
Auto Scaling VMs on AWS, GCP, and Azure
How Auto Scaling groups, managed instance groups and Virtual Machine Scale Sets add and remove VMs, and how to tune them so scaling is fast and calm.
Generative AI
Conditional GANs: Controlling the Output
How conditional GANs let you choose what the generator makes: label inputs, AC-GAN, the projection discriminator, conditional batch norm and pix2pix, with PyTorch code.
AI & ML
Decision Trees: Making Decisions Using Data
How decision trees learn yes-or-no questions from data: Gini and entropy, overfitting and pruning, regression trees, and working scikit-learn code.