Dave Ebbelaar · 28 min · intermediate · English

OpenAI Function Calling - Full Beginner Tutorial

pixegami · 17 min · intermediate · English

RAG + Langchain Python Project: Easy AI/Chat For Your Docs

Tech With Tim · 33 min · intermediate · English

Please Learn How To Write Tests in Python - Pytest Tutorial

Hynek Schlawack · 24 min · intermediate · English

My 2025 uv-based Python Project Layout for Production Apps

Kevin Stratvert · 46 min · beginner · English

Git and GitHub Tutorial for Beginners

Jay Feng · 12 min · intermediate · English

Ace your next BEHAVIORAL INTERVIEW + Data Science Tips

Exponent · 30 min · advanced · English

Machine Learning System Design Interview: YouTube Recommendations

Optional second angle: candidate-generation + ranking architecture worked through on the classic YouTube recommendation prompt.

Exponent · 53 min · advanced · English

Spotify ML Question - Design a Recommendation System (Full mock interview)

Full mock interview showing a repeatable end-to-end framework: problem framing, data/features, model, serving and monitoring.

Simplilearn · 35 min · intermediate · English

Machine Learning Interview Questions And Answers | ML Interview Questions And Answers | Simplilearn

Rapid-fire ML theory questions (bias-variance, regularization, metrics) with model answers for the fundamentals round.

No More Tutorials · 15 min · beginner · English

4 *Real* Machine Learning Projects That Get You Hired - No More Tutorials!

What hireable ML portfolio projects/case studies actually look like, beyond copied tutorials.

Python Engineer · 25 min · intermediate · English

Create & Deploy A Deep Learning App - PyTorch Model Deployment With Flask & Heroku

Build and deploy a PyTorch deep-learning app end to end with a Flask REST API on Heroku (digit classifier with live demo).

Shaw Talebi · 29 min · intermediate · English

How to Deploy ML Solutions with FastAPI, Docker, & AWS

Deploy an ML model as a production service with FastAPI, Docker and AWS.

Krish Naik · 40 min · intermediate · English

End To End Machine Learning Project Implementation Using AWS Sagemaker

Complete end-to-end ML build and cloud deployment on AWS SageMaker: train, deploy and serve.

Google Cloud Tech · 7 min · intermediate · English

Build a custom ML model with Vertex AI

Optional Vertex AI counterpart: custom container training, model registry, and endpoint deployment on Google Cloud.

Amazon Web Services · 50 min · beginner · English

How to build, train, and deploy machine learning models using Amazon SageMaker

Official AWS Tech Talk walking through the full build-train-deploy workflow on the managed SageMaker platform.

PyTorch · 13 min · intermediate · English

Part 3: Multi-GPU training with DDP (code walkthrough)

Official PyTorch code walkthrough of DistributedDataParallel: process groups, DistributedSampler, and multi-GPU data parallelism.

Efficient NLP · 13 min · intermediate · English

Quantization vs Pruning vs Distillation: Optimizing NNs for Inference

Compares all three compression techniques and the distill-then-quantize-then-prune pipeline for faster, cheaper inference.

Krish Naik · 50 min · intermediate · English

Evidently AI Tutorial-Open Source ML Models Monitoring and Observability

Monitor deployed models and detect data/target drift with Evidently AI

Iterative · 11 min · intermediate · English

CML - CI/CD for Machine Learning with GitHub Actions & GitLab CI

Automate training, evaluation, and reporting in CI pipelines with CML + GitHub Actions

Prodramp · 33 min · intermediate · English

An AI Engineer technical guide to Feature Store with FEAST

Different-angle: feature store concepts and hands-on Feast setup for consistent feature serving

CodeKamikaze · 14 min · beginner · English

Introduction to DVC | Data Version Control for ML Projects | @CodeKamikaze | MlOps (1)

Versioning data and ML pipelines with DVC

Weights & Biases · 15 min · intermediate · English

Weights & Biases End-to-End Demo

The W&B half: end-to-end demo tracking runs, metrics and artifacts reproducibly in the cloud.

codebasics · 51 min · intermediate · English

MLFlow Tutorial | ML Ops Tutorial

Hands-on MLflow: log params/metrics/artifacts, experiment tracking and the model registry.

PyTorch · 13 min · intermediate · English

Introduction to TorchServe, an open-source model serving library for PyTorch

Official intro to the TorchServe half: serving PyTorch models at scale with default handlers.

Nicolai Nielsen · 17 min · intermediate · English

Deploying Pytorch Neural Network Classification Using the ONNX Format

Hands-on export of a PyTorch model to ONNX and running portable inference with ONNX Runtime.

Python Simplified · 26 min · intermediate · English

Docker Simply Explained with a Machine Learning Project for Beginners

Containerize an ML project with Docker step by step: Dockerfile, image build and run.

NeuralNine · 40 min · intermediate · English

Kubernetes Tutorial: Deploy Machine Learning Models with Docker and FastAPI

Packages an ML+FastAPI service in Docker, then deploys and scales it on Kubernetes - the exact topic flow.

DataTalksClub · 58 min · intermediate · English

How to Deploy Machine Learning Models with FastAPI, Docker, and Fly.io | End-to-End Tutorial

End-to-end: wrap a trained model in a FastAPI REST API with Pydantic, then containerize and ship it.

AssemblyAI · 14 min · beginner · English

Getting Started With Hugging Face in 15 Minutes | Transformers, Pipeline, Tokenizer, Models

Practical intro to using pretrained transformers via pipelines, tokenizers, and models for NLP tasks.

3Blue1Brown · 26 min · intermediate · English

Attention in transformers, visually explained | Chapter 6, Deep Learning

Different angle: step-by-step visualization of the self-attention mechanism (Q/K/V) itself.

3Blue1Brown · 27 min · intermediate · English

Transformers, the tech behind LLMs | Deep Learning Chapter 5

Visual, intuition-first explanation of the transformer architecture and why it dominates modern AI.

Patrick Loeber · 15 min · intermediate · English

PyTorch Tutorial 15 - Transfer Learning

Clean, self-contained walkthrough of fine-tuning a pretrained ResNet (feature extraction vs full fine-tune) in PyTorch.

NeuralNine · 31 min · intermediate · English

Image Classification CNN in PyTorch

Hands-on different angle: builds and trains a CNN image classifier on CIFAR-10 in PyTorch.

Computerphile · 14 min · beginner · English

CNN: Convolutional Neural Networks Explained - Computerphile

Dr Mike Pound's intuitive, visual explanation of how convolutions and CNN layers work for image classification.

Abhishek Thakur · 10 min · intermediate · English

8. Training and validation loops in PyTorch

Structure a robust train and validation loop in PyTorch.

Patrick Loeber · 14 min · intermediate · English

PyTorch Tutorial 06 - Training Pipeline: Model, Loss, and Optimizer

Build the core PyTorch training pipeline: model, loss function, optimizer and the update loop.

AssemblyAI · 50 min · beginner · English

PyTorch Crash Course - Getting Started with Deep Learning

Optional fast track: tensors and autograd in under an hour.

3Blue1Brown · 10 min · intermediate · English

Backpropagation calculus | Deep Learning, chapter 4

Optional deeper angle: the chain-rule math behind backpropagation.

3Blue1Brown · 19 min · beginner · English

But what is a Neural Network? | Deep learning, chapter 1

Visual intuition for neurons, layers, weights and biases via handwritten-digit recognition.

NeuralNine · 24 min · intermediate · English

Building a Machine Learning Pipeline with Python and Scikit-Learn | Step-by-Step Tutorial

Bundles preprocessing + model with Pipeline/ColumnTransformer so the same transforms run at train and inference, killing leakage.

Decoding Data Science · 28 min · intermediate · English

Mastering Hyperparameter Tuning with Optuna: Boost Your Machine Learning Models!

Hands-on Optuna walkthrough: define-by-run search space, study/trial objects, and Bayesian/TPE optimization over many trials.

StatQuest with Josh Starmer · 20 min · intermediate · English

Regularization Part 1: Ridge (L2) Regression

Visual intuition for how L2 penalties shrink coefficients to reduce variance and fight overfitting; pairs with the Lasso (L1) follow-up.

StatQuest with Josh Starmer · 6 min · intermediate · English

Machine Learning Fundamentals: Cross Validation

Optional companion: why k-fold cross-validation gives honest performance estimates instead of a lucky split.

StatQuest with Josh Starmer · 17 min · intermediate · English

ROC and AUC, Clearly Explained!

Builds confusion-matrix, sensitivity/specificity, ROC and AUC intuition for picking thresholds on imbalanced data.

StatQuest with Josh Starmer · 22 min · intermediate · English

StatQuest: Principal Component Analysis (PCA), Step-by-Step

Dimensionality reduction / feature engineering: PCA via SVD, loading scores and scree plots.

StatQuest with Josh Starmer · 9 min · beginner · English

StatQuest: K-means clustering

How k-means groups unlabeled data and how to pick the best value of K.

StatQuest with Josh Starmer · 57 min · intermediate · English

XGBoost in Python from Start to Finish

Practical angle: train, cross-validate and tune an XGBoost model in Python end to end.

StatQuest with Josh Starmer · 25 min · intermediate · English

XGBoost Part 1 (of 4): Regression

How gradient-boosted trees work conceptually: similarity scores, gain, pruning and regularization for tabular data.

codebasics · 16 min · intermediate · English

Machine Learning Tutorial Python - 18: K nearest neighbors classification with python code

kNN classification with scikit-learn: choosing k, fit/predict and evaluation.

codebasics · 23 min · intermediate · English

Machine Learning Tutorial Python - 10 Support Vector Machine (SVM)

SVM with scikit-learn in depth: margins, the kernel trick and fitting a classifier.