AI & MLMachine Learning Algorithms
How decision trees learn yes-or-no questions from data: Gini and entropy, overfitting and pruning, regression trees, and working scikit-learn code.
Read the articleCloud
How on-demand, reservations, savings plans, committed use discounts and Spot pricing work on AWS, GCP and Azure, and how to combine them safely.
Generative AI
Why GAN training breaks, how to read the signs, and the fixes that work: a solid DCGAN baseline, loss choices, spectral norm, R1, EMA and a debugging checklist.
AI & ML
How logistic regression turns a weighted sum into a probability: the sigmoid, log loss, odds ratios, thresholds, imbalance and scikit-learn code.
Recently published
How to read and choose VM instance types on AWS, GCP and Azure: families, memory ratios, CPU architectures, burstable credits, local disks and rightsizing.
Build a convolutional variational autoencoder in PyTorch: data, encoder, decoder, loss, KL warm-up, evaluation, sampling and checkpoints.
How linear regression predicts numbers: the model, least squares, gradient descent, scikit-learn code, the assumptions that matter and when to regularize.
EC2, Compute Engine and Azure VMs side by side: naming, families, disks, maintenance, stop billing, Spot, discounts and SLAs, and how to choose.
Where the VAE loss comes from: latent variable models, the evidence lower bound, the closed-form KL term and the reparameterization trick, with PyTorch code.
The machine learning vocabulary you need: features, labels, parameters, hyperparameters, splits, overfitting, metrics and leakage, with runnable examples.
Learning paths
Three series that build on each other: start with the cloud, meet the machines that learn, then watch them create.
Cloud computing
Foundations of the cloud and hands-on tours of AWS, Google Cloud and Azure — from your first VM to multi-cloud strategy.
AI & machine learning
How machines learn: the history of AI, supervised and unsupervised learning, model training and the data behind it all.
Generative AI
Transformers, GANs, VAEs and GPT — what generative AI is, how it works, and how the cloud providers put it to work.
Quick quiz
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).