Skip to content
Datamewby Intura
Start free

All lessons

Every lesson on Datamew, grouped by track and module. Lessons marked free can be read in full right here, no account needed. The rest come with their track and open in the learning app.

166 lessons · 10 free to read now

Free to read now

Complete lessons, open to everyone. Each one is the start of a module, so it is a fair sample of the rest.

Python for Data Science

3 modules · 4 lessons

Module 1Start Here

  1. Why Python for DataFree
  2. Reading a Traceback to the End (Included with the track)

Module 2The Data Structures You Use Daily

  1. Lists and Dicts (Included with the track)

Module 3pandas, Until You Trust It

  1. DataFrames and Cleaning (Included with the track)
Every lesson in Python for Data Science, with summaries

Data Analytics: Statistics & Data Visualization

9 modules · 23 lessons

Module 1Correlation

  1. What Correlation Actually MeasuresFree

Module 2Bayesian

  1. Inverting a Probability (Included with the track)

Module 3Sampling & Hypothesis Testing

  1. The Central Limit Theorem (Included with the track)
  2. p-Values and Statistical Power (Included with the track)
  3. Confidence Intervals (Included with the track)

Module 4A/B Testing

  1. Designing an Experiment (Included with the track)
  2. Sample Size and Duration (Included with the track)
  3. Analysing A/B Test Results (Included with the track)
  4. A/B Testing Pitfalls (Included with the track)

Module 5Regression for Analysts

  1. Simple Linear Regression (Included with the track)
  2. Multiple Regression and Confounders (Included with the track)
  3. Regression Diagnostics (Included with the track)

Module 6Choosing the Right Chart

  1. Plot Before You SummariseFree
  2. Charts for Presentation (Included with the track)
  3. Colour and Accessibility (Included with the track)

Module 7Python Data Visualization with matplotlib & seaborn

  1. The Anatomy of a matplotlib Figure (Included with the track)
  2. Statistical Plots with seaborn (Included with the track)
  3. Interactive Charts with plotly (Included with the track)

Module 8Dashboards & Data Storytelling

  1. Designing Dashboards (Included with the track)
  2. Choosing KPIs (Included with the track)
  3. Data Storytelling (Included with the track)

Module 9Misleading Charts

  1. Truncated and Dual Axes (Included with the track)
  2. Cherry-Picked Ranges and Deceptive Areas (Included with the track)
Every lesson in Data Analytics: Statistics & Data Visualization, with summaries

Introduction to Machine Learning

12 modules · 21 lessons

Module 1Getting Started

  1. Supervised, Unsupervised, ReinforcementFree
  2. Categorical vs Numerical, Structured vs Unstructured (Included with the track)

Module 2Dataset Splitting, Cross-Validation, Data Leakage

  1. Splitting Data, and K-Fold (Included with the track)
  2. Data Leakage (Included with the track)

Module 3Training, Evaluation, Bias–Variance, Tuning

  1. Choosing the Right Metric (Included with the track)
  2. Bias–Variance Trade-off (Included with the track)
  3. Hyperparameter Tuning (Included with the track)

Module 4KNN — Classifier and Regressor

  1. How KNN Decides (Included with the track)

Module 5SVM — Classifier and Regressor

  1. Margin, C, and Kernels (Included with the track)

Module 6Linear Regression

  1. Finding the Best Line (Included with the track)

Module 7Logistic Regression

  1. Sigmoid, Log-Odds, and the Threshold (Included with the track)

Module 8Decision Tree, Random Forest, Gradient Boosting

  1. From One Tree to a Forest (Included with the track)

Module 9Feature Engineering

  1. Building Features That Help (Included with the track)

Module 10Explainable AI: Feature Importance, PDP, SHAP

  1. Three Questions, Three Tools (Included with the track)

Module 11Unsupervised Learning: Clustering & Dimensionality Reduction

  1. Clustering with K-Means (Included with the track)
  2. Principal Component Analysis (PCA) (Included with the track)
  3. DBSCAN, Hierarchical Clustering and Gaussian Mixtures (Included with the track)

Module 12Recommendation Systems

  1. What a Recommender Predicts (Included with the track)
  2. Content-Based Filtering (Included with the track)
  3. Collaborative Filtering (Included with the track)
  4. Evaluating and Combining Recommenders (Included with the track)
Every lesson in Introduction to Machine Learning, with summaries

Introduction to Deep Learning & Neural Networks

6 modules · 21 lessons

Module 1Neural Network Foundations

  1. What a Neural Network Actually ComputesFree
  2. Activation Functions: ReLU, GELU and Friends (Included with the track)
  3. Backpropagation Without the Fear (Included with the track)
  4. Your First Training Loop in PyTorch (Included with the track)

Module 2Training Deep Networks

  1. Optimizers: SGD, Momentum, Adam (Included with the track)
  2. Learning-Rate Schedules and Warmup (Included with the track)
  3. Initialisation and Normalisation (Included with the track)
  4. Regularisation: Dropout, Weight Decay, Early Stopping (Included with the track)

Module 3PyTorch for Deep Learning

  1. Tensors and Autograd (Included with the track)
  2. Building Models with nn.Module (Included with the track)
  3. Datasets and DataLoaders (Included with the track)
  4. GPUs and Mixed Precision (Included with the track)

Module 4Convolutional Neural Networks

  1. How Convolutions Work (Included with the track)
  2. CNN Architectures: from LeNet to ResNet (Included with the track)
  3. Transfer Learning (Included with the track)

Module 5Sequence Models and Transformers

  1. RNNs and LSTMs (Included with the track)
  2. The Attention Mechanism (Included with the track)
  3. The Transformer Architecture (Included with the track)

Module 6Deep Learning in Practice

  1. Debugging Neural Networks (Included with the track)
  2. Tracking Experiments (Included with the track)
  3. Capstone: an Image Classifier (Included with the track)
Every lesson in Introduction to Deep Learning & Neural Networks, with summaries

LLMs, Prompt Engineering & Context Engineering

6 modules · 22 lessons

Module 1How LLMs Work

  1. How an LLM Reads Your PromptFree
  2. Next-Token Prediction and Sampling (Included with the track)
  3. Context Windows and Token Costs (Included with the track)
  4. Choosing a Model (Included with the track)

Module 2Prompt Engineering Fundamentals

  1. Clear Instructions and Roles (Included with the track)
  2. Few-Shot Examples (Included with the track)
  3. Reasoning and Chain-of-Thought (Included with the track)
  4. Structured Output (Included with the track)

Module 3Context Engineering

  1. What Goes in the Context (Included with the track)
  2. Retrieval-Augmented Generation (RAG) (Included with the track)
  3. Long-Context Pitfalls (Included with the track)
  4. Memory and Conversation State (Included with the track)

Module 4Building with LLM APIs

  1. Your First API Call (Included with the track)
  2. Tool Calling (Included with the track)
  3. Cost, Latency and Caching (Included with the track)
  4. Retries and Rate Limits (Included with the track)

Module 5Evaluating LLM Applications

  1. Building an Eval Set (Included with the track)
  2. LLM as a Judge (Included with the track)
  3. Regression-Testing Prompts (Included with the track)

Module 6LLM Safety and Reliability

  1. Hallucinations and Grounding (Included with the track)
  2. Prompt Injection (Included with the track)
  3. Guardrails and Monitoring (Included with the track)
Every lesson in LLMs, Prompt Engineering & Context Engineering, with summaries

Building AI Agents: Harness Engineering

6 modules · 20 lessons

Module 1AI Agent Fundamentals

  1. What Makes Something an AgentFree
  2. Designing Tools for Agents (Included with the track)
  3. Workflows versus Agents (Included with the track)
  4. Build an Agent from Scratch (Included with the track)

Module 2Harness Engineering

  1. Context Management in Agent Loops (Included with the track)
  2. Permissions and Sandboxing (Included with the track)
  3. Error Handling and Recovery (Included with the track)
  4. Observability and Tracing (Included with the track)

Module 3Tools and the Model Context Protocol

  1. Tool Interfaces That Work (Included with the track)
  2. The Model Context Protocol (MCP) (Included with the track)
  3. Agents on Databases and APIs (Included with the track)

Module 4Multi-Agent Systems

  1. The Orchestrator-Worker Pattern (Included with the track)
  2. Subagents and Context Isolation (Included with the track)
  3. When Multi-Agent Hurts (Included with the track)

Module 5Evaluating Agents

  1. Task-Level Evals (Included with the track)
  2. Reading Agent Trajectories (Included with the track)
  3. Cost and Reliability Metrics (Included with the track)

Module 6Shipping Agents to Production

  1. Human-in-the-Loop (Included with the track)
  2. Agent Security and Prompt Injection (Included with the track)
  3. Capstone: a Research Agent (Included with the track)
Every lesson in Building AI Agents: Harness Engineering, with summaries

MLOps: Deploying Machine Learning & Deep Learning Models

6 modules · 19 lessons

Module 1ML Systems in Production

  1. Why Models Decay in ProductionFree
  2. Training-Serving Skew (Included with the track)
  3. Batch vs Online Inference (Included with the track)
  4. An ML System Design Checklist (Included with the track)

Module 2Packaging and Serving Models

  1. Saving Models Reproducibly (Included with the track)
  2. A Model API with FastAPI (Included with the track)
  3. Containerising with Docker (Included with the track)

Module 3Serving Deep Learning Models and LLMs

  1. Latency, Throughput and Batching (Included with the track)
  2. ONNX and Model Optimisation (Included with the track)
  3. Quantisation (Included with the track)
  4. Serving LLMs (Included with the track)

Module 4ML Pipelines and CI/CD

  1. Experiment Tracking and the Model Registry (Included with the track)
  2. Training Pipelines (Included with the track)
  3. CI/CD for Machine Learning (Included with the track)

Module 5Monitoring and Retraining

  1. Detecting Data Drift (Included with the track)
  2. Retraining Strategies (Included with the track)
  3. Shadow and Canary Deployments (Included with the track)

Module 6MLOps Capstone

  1. Choosing Cloud Infrastructure (Included with the track)
  2. Capstone: Deploy and Monitor (Included with the track)
Every lesson in MLOps: Deploying Machine Learning & Deep Learning Models, with summaries

Computer Vision with Deep Learning

6 modules · 17 lessons

Module 1Image Fundamentals

  1. How Computers See ImagesFree
  2. Image Preprocessing and Augmentation (Included with the track)
  3. Pooling and Receptive Fields (Included with the track)

Module 2Image Classification with CNNs

  1. Building a CNN in PyTorch (Included with the track)
  2. Transfer Learning with Pretrained Backbones (Included with the track)
  3. Evaluating Image Classifiers (Included with the track)

Module 3Object Detection

  1. Bounding Boxes and IoU (Included with the track)
  2. One-Stage Detectors: YOLO (Included with the track)
  3. Training a Custom Detector (Included with the track)

Module 4Image Segmentation

  1. Semantic vs Instance Segmentation (Included with the track)
  2. U-Net (Included with the track)
  3. Promptable Segmentation Models (Included with the track)

Module 5Vision Transformers and Multimodal Models

  1. Vision Transformers (ViT) (Included with the track)
  2. CLIP and Image-Text Embeddings (Included with the track)
  3. Vision-Language Models (Included with the track)

Module 6Computer Vision in Production

  1. Edge and Mobile Deployment (Included with the track)
  2. Capstone: a Vision System (Included with the track)
Every lesson in Computer Vision with Deep Learning, with summaries

Natural Language Processing (NLP)

6 modules · 19 lessons

Module 1Representing Text

  1. From Words to VectorsFree
  2. Tokenisation for NLP (Included with the track)
  3. TF-IDF and Classic Text Features (Included with the track)

Module 2Text Classification

  1. Text Preprocessing Pipelines (Included with the track)
  2. Classic Text Classifiers (Included with the track)
  3. Fine-Tuning Transformers for Classification (Included with the track)
  4. Classification with LLMs (Included with the track)

Module 3Information Extraction

  1. Named Entity Recognition (Included with the track)
  2. Structured Extraction with LLMs (Included with the track)
  3. Evaluating Extraction (Included with the track)

Module 4Transformers for NLP

  1. Encoders and Decoders (Included with the track)
  2. Pretrained Language Models (Included with the track)
  3. Hugging Face in Practice (Included with the track)

Module 5Semantic Search and Sentence Embeddings

  1. Sentence Embeddings (Included with the track)
  2. Vector Databases (Included with the track)
  3. Hybrid Search and Evaluation (Included with the track)

Module 6NLP for Indonesian

  1. Challenges of Indonesian Text (Included with the track)
  2. Indonesian NLP Resources (Included with the track)
  3. Capstone: a Review Analyser (Included with the track)
Every lesson in Natural Language Processing (NLP), with summaries