Local static search

Search by concept, tool, failure, or decision.

Use / or Cmd/Ctrl + K from anywhere. Results require no server or analytics.

80 results

Course

Engineering foundations

A churn notebook cannot be reproduced by the teammate expected to ship it. A seeded, tested, packaged, versioned training workflow with a model card.

role:platform · lifecycle:training · concept:reproducibility
Course

Problem framing, statistics & evaluation

An ETA model improves RMSE while increasing missed-delivery cost. A metric contract, leakage-safe validation, calibration analysis, and experiment plan.

lifecycle:evaluation · concept:calibration · concept:uncertainty
Course

Data & feature foundations

Fraud labels arrive late and online features disagree with training data. Data contracts, point-in-time features, backfills, quality gates, and lineage.

lifecycle:data · failure:training-serving-skew · role:platform
Course

Linear, probabilistic, neighbor & margin models

Support tickets need explainable routing under a 15 ms latency budget. A justified baseline across regression, Naive Bayes, kNN, and SVM.

algorithm:knn · algorithm:svm · modality:tabular
Course

Trees, forests & gradient boosting

A marketplace must catch rare fraud without blocking trustworthy sellers. Calibrated random-forest and XGBoost baselines with cost-sensitive thresholds.

algorithm:random-forest · algorithm:xgboost · concept:calibration
Course

Unsupervised learning, anomalies & retrieval

Novel equipment failures appear before reliable labels exist. A PCA, clustering, anomaly, and nearest-neighbor retrieval investigation.

algorithm:pca · concept:embeddings · lifecycle:evaluation
Course

Forecasting & temporal ML

Regional demand shifts through promotions, holidays, and drift. Rolling validation, statistical baselines, boosted forecasts, and uncertainty bands.

modality:time-series · concept:uncertainty · failure:drift
Course

Recommendation, search & ranking

Marketplace ranking learns from biased clicks and reinforces its own mistakes. Candidate generation, ranking metrics, debiasing, and online experiment design.

track:recommendation-search · failure:feedback-loop · concept:embeddings
Course

Neural networks from scratch

A nonlinear sensor classifier defeats every classical baseline. A small network built from forward pass through backpropagation and optimization.

concept:backpropagation · lifecycle:training · tool:pytorch
Course

Image ML

A factory has few positive examples of costly visual defects. CNN and transfer-learning baselines with augmentation, calibration, and monitoring.

modality:image · algorithm:cnn · track:vision-multimodal
Course

Sequence ML: RNNs, GRUs & LSTMs

Long support conversations must be routed while preserving temporal context. A masked sequence model with BPTT, recurrent gates, and attention precursors.

modality:text · algorithm:lstm · track:nlp-llm
Course

GPU-aware training

Training repeatedly OOMs and misses its nightly completion window. A profiled, mixed-precision, memory-budgeted training loop.

tool:cuda · failure:oom · lifecycle:training
Course

Distributed & fault-tolerant training

An eight-GPU job is slower than one GPU and loses progress on failure. Efficient DDP, parallelism choices, elastic sampling, and resumable checkpoints.

concept:all-reduce · tool:pytorch · role:platform
Course

Build a transformer from scratch

Domain autocomplete needs a model whose every component the team can explain. Tokenizer, attention, RoPE, residual stack, training loop, generation, and KV cache.

concept:attention · algorithm:transformer · track:nlp-llm
Course

Foundation-model lifecycle

A private support assistant must answer from evidence and resist manipulation. A grounded system design spanning adaptation, RAG, evaluation, and safety.

concept:rag · concept:evaluation · failure:prompt-injection
Course

Frontier architectures & efficient inference

Long-context generation breaks latency and cost targets. A capacity plan using efficient attention, quantization, batching, and modern routing.

concept:kv-cache · tool:vllm · lifecycle:inference
Course

Production data & ML platforms

A late feature silently corrupts every downstream prediction. A traced batch/stream platform with orchestration, registry, lineage, and ownership.

tool:kafka · tool:mlflow · role:platform
Course

Serving & inference systems

Launch traffic causes p99 spikes and leaves expensive GPUs idle. Batch and online paths with batching, autoscaling, load tests, canaries, and rollback.

lifecycle:inference · tool:triton · failure:latency
Course

Reliability, monitoring & experimentation

Model quality decays while every infrastructure dashboard stays green. Joined data/model/service telemetry, drift policy, experiments, alerts, and runbooks.

failure:drift · lifecycle:monitoring · role:reliability
Course

Governance, fairness, privacy & security

A high-performing system creates subgroup harm and leaks sensitive information. A launch review covering fairness, privacy, licensing, abuse, security, and response.

concept:fairness · concept:privacy · failure:supply-chain
Lesson

From notebook to reproducible run

Use from notebook to reproducible run to move the engineering foundations production brief toward a defensible release.

role:platform · lifecycle:training · concept:reproducibility
Lesson

Contracts before models

Use contracts before models to move the engineering foundations production brief toward a defensible release.

role:platform · lifecycle:training · concept:reproducibility
Lesson

Training code is product code

Use training code is product code to move the engineering foundations production brief toward a defensible release.

role:platform · lifecycle:training · concept:reproducibility
Lesson

Containers and configuration without surprises

Use containers and configuration without surprises to move the engineering foundations production brief toward a defensible release.

role:platform · lifecycle:training · concept:reproducibility
Lesson

Observable, idempotent, failure-safe workflows

Use observable, idempotent, failure-safe workflows to move the engineering foundations production brief toward a defensible release.

role:platform · lifecycle:training · concept:reproducibility
Lesson

Read a research paper as an executable specification

Turn a research paper into a testable claim map, implementation contract, and prioritized reading plan before writing code.

role:platform · lifecycle:training · concept:reproducibility
Lesson

Reproduce, validate, and productionize a paper

Implement a paper from baseline to novel component, diagnose reproduction gaps, and adapt it for production without silently changing its claim.

role:platform · lifecycle:training · concept:reproducibility
Lesson

Predict decisions, not just labels

Use predict decisions, not just labels to move the evaluation production brief toward a defensible release.

lifecycle:evaluation · concept:calibration · concept:uncertainty
Lesson

Labels, availability, and leakage

Use labels, availability, and leakage to move the evaluation production brief toward a defensible release.

lifecycle:evaluation · concept:calibration · concept:uncertainty
Lesson

Baselines and honest splits

Use baselines and honest splits to move the evaluation production brief toward a defensible release.

lifecycle:evaluation · concept:calibration · concept:uncertainty
Lesson

Metrics, thresholds, and calibration

Use metrics, thresholds, and calibration to move the evaluation production brief toward a defensible release.

lifecycle:evaluation · concept:calibration · concept:uncertainty
Lesson

Uncertainty and online experiments

Use uncertainty and online experiments to move the evaluation production brief toward a defensible release.

lifecycle:evaluation · concept:calibration · concept:uncertainty
Lesson

Metric selection by task and decision

Select metrics from the prediction target, decision, error costs, prevalence, slices, horizon, and deployment constraints—not from habit.

lifecycle:evaluation · concept:calibration · concept:uncertainty
Lesson

Data contracts, ownership, and lineage

Use data contracts, ownership, and lineage to move the data & features production brief toward a defensible release.

lifecycle:data · failure:training-serving-skew · role:platform
Lesson

Point-in-time-correct features

Use point-in-time-correct features to move the data & features production brief toward a defensible release.

lifecycle:data · failure:training-serving-skew · role:platform
Lesson

Feature transformations that survive production

Use feature transformations that survive production to move the data & features production brief toward a defensible release.

lifecycle:data · failure:training-serving-skew · role:platform
Lesson

Batch, stream, and training-serving parity

Use batch, stream, and training-serving parity to move the data & features production brief toward a defensible release.

lifecycle:data · failure:training-serving-skew · role:platform
Lesson

Labels, snapshots, and backfills

Use labels, snapshots, and backfills to move the data & features production brief toward a defensible release.

lifecycle:data · failure:training-serving-skew · role:platform
Lesson

Linear regression as a production baseline

Use linear regression as a production baseline to move the classical baselines production brief toward a defensible release.

algorithm:knn · algorithm:svm · modality:tabular
Lesson

Logistic regression, odds, and calibration

Use logistic regression, odds, and calibration to move the classical baselines production brief toward a defensible release.

algorithm:knn · algorithm:svm · modality:tabular
Lesson

Naive Bayes under sparse data

Use naive bayes under sparse data to move the classical baselines production brief toward a defensible release.

algorithm:knn · algorithm:svm · modality:tabular
Lesson

kNN, distance, and local decisions

Use knn, distance, and local decisions to move the classical baselines production brief toward a defensible release.

algorithm:knn · algorithm:svm · modality:tabular
Lesson

SVMs, margins, and kernels

Use svms, margins, and kernels to move the classical baselines production brief toward a defensible release.

algorithm:knn · algorithm:svm · modality:tabular
Lesson

Trees as learned decision rules

Use trees as learned decision rules to move the trees & boosting production brief toward a defensible release.

algorithm:random-forest · algorithm:xgboost · concept:calibration
Lesson

Random forests and diversity

Use random forests and diversity to move the trees & boosting production brief toward a defensible release.

algorithm:random-forest · algorithm:xgboost · concept:calibration
Lesson

Gradient boosting as error correction

Use gradient boosting as error correction to move the trees & boosting production brief toward a defensible release.

algorithm:random-forest · algorithm:xgboost · concept:calibration
Lesson

XGBoost: regularized boosting at scale

Use xgboost: regularized boosting at scale to move the trees & boosting production brief toward a defensible release.

algorithm:random-forest · algorithm:xgboost · concept:calibration
Lesson

Calibrating and explaining ensembles

Use calibrating and explaining ensembles to move the trees & boosting production brief toward a defensible release.

algorithm:random-forest · algorithm:xgboost · concept:calibration
Lesson

PCA and representation geometry

Use pca and representation geometry to move the unsupervised & retrieval production brief toward a defensible release.

algorithm:pca · concept:embeddings · lifecycle:evaluation
Lesson

Clustering as an operational hypothesis

Use clustering as an operational hypothesis to move the unsupervised & retrieval production brief toward a defensible release.

algorithm:pca · concept:embeddings · lifecycle:evaluation
Lesson

Density clusters and novel anomalies

Use density clusters and novel anomalies to move the unsupervised & retrieval production brief toward a defensible release.

algorithm:pca · concept:embeddings · lifecycle:evaluation
Lesson

Embeddings and similarity

Use embeddings and similarity to move the unsupervised & retrieval production brief toward a defensible release.

algorithm:pca · concept:embeddings · lifecycle:evaluation
Lesson

Approximate retrieval under latency

Use approximate retrieval under latency to move the unsupervised & retrieval production brief toward a defensible release.

algorithm:pca · concept:embeddings · lifecycle:evaluation
Lesson

Forecast contracts and naive models

Use forecast contracts and naive models to move the forecasting production brief toward a defensible release.

modality:time-series · concept:uncertainty · failure:drift
Lesson

Trend, seasonality, and known-future signals

Use trend, seasonality, and known-future signals to move the forecasting production brief toward a defensible release.

modality:time-series · concept:uncertainty · failure:drift
Lesson

Backtesting without time travel

Use backtesting without time travel to move the forecasting production brief toward a defensible release.

modality:time-series · concept:uncertainty · failure:drift
Lesson

Statistical and ML forecasters

Use statistical and ml forecasters to move the forecasting production brief toward a defensible release.

modality:time-series · concept:uncertainty · failure:drift
Lesson

Intervals, drift, and forecast operations

Use intervals, drift, and forecast operations to move the forecasting production brief toward a defensible release.

modality:time-series · concept:uncertainty · failure:drift
Lesson

From corpus to slate: retrieve, score, re-rank

Use from corpus to slate: retrieve, score, re-rank to move the ranking systems production brief toward a defensible release.

track:recommendation-search · failure:feedback-loop · concept:embeddings
Lesson

Clicks are not labels

Use clicks are not labels to move the ranking systems production brief toward a defensible release.

track:recommendation-search · failure:feedback-loop · concept:embeddings
Lesson

BM25, factorization, two towers, and ANN

Use bm25, factorization, two towers, and ann to move the ranking systems production brief toward a defensible release.

track:recommendation-search · failure:feedback-loop · concept:embeddings
Lesson

Pointwise, pairwise, and listwise ranking

Use pointwise, pairwise, and listwise ranking to move the ranking systems production brief toward a defensible release.

track:recommendation-search · failure:feedback-loop · concept:embeddings
Lesson

Serving freshness, diversity, and experiments

Use serving freshness, diversity, and experiments to move the ranking systems production brief toward a defensible release.

track:recommendation-search · failure:feedback-loop · concept:embeddings
Lesson

Beyond linear boundaries

Use beyond linear boundaries to move the neural networks production brief toward a defensible release.

concept:backpropagation · lifecycle:training · tool:pytorch
Lesson

Forward pass, activations, losses, and initialization

Use forward pass, activations, losses, and initialization to move the neural networks production brief toward a defensible release.

concept:backpropagation · lifecycle:training · tool:pytorch
Lesson

Backpropagation without magic

Use backpropagation without magic to move the neural networks production brief toward a defensible release.

concept:backpropagation · lifecycle:training · tool:pytorch
Lesson

SGD, momentum, AdamW, and schedules

Use sgd, momentum, adamw, and schedules to move the neural networks production brief toward a defensible release.

concept:backpropagation · lifecycle:training · tool:pytorch
Lesson

Regularize, normalize, debug, and ship

Use regularize, normalize, debug, and ship to move the neural networks production brief toward a defensible release.

concept:backpropagation · lifecycle:training · tool:pytorch
Lesson

Activation functions: geometry, gradients, and failure modes

Select activation functions by signal range, gradient flow, architecture, precision, and failure mode; then diagnose saturation and dead units from telemetry.

concept:backpropagation · lifecycle:training · tool:pytorch
Lesson

Loss functions by task, data, and deployment constraints

Choose and debug training objectives as optimization surrogates for the real task, including imbalance, outliers, uncertainty, ranking, dense prediction, and generation.

concept:backpropagation · lifecycle:training · tool:pytorch
Lesson

Images are data contracts

Use images are data contracts to move the vision production brief toward a defensible release.

modality:image · algorithm:cnn · track:vision-multimodal
Lesson

Convolution under the microscope

Use convolution under the microscope to move the vision production brief toward a defensible release.

modality:image · algorithm:cnn · track:vision-multimodal
Lesson

Receptive fields, normalization, and residuals

Use receptive fields, normalization, and residuals to move the vision production brief toward a defensible release.

modality:image · algorithm:cnn · track:vision-multimodal
Lesson

Transfer learning for classification, detection, and segmentation

Use transfer learning for classification, detection, and segmentation to move the vision production brief toward a defensible release.

modality:image · algorithm:cnn · track:vision-multimodal
Lesson

Vision in the wild: thresholds, latency, and drift

Use vision in the wild: thresholds, latency, and drift to move the vision production brief toward a defensible release.

modality:image · algorithm:cnn · track:vision-multimodal
Lesson

Sequences are not IID

Use sequences are not iid to move the sequence models production brief toward a defensible release.

modality:text · algorithm:lstm · track:nlp-llm
Lesson

Recurrent state and BPTT

Use recurrent state and bptt to move the sequence models production brief toward a defensible release.

modality:text · algorithm:lstm · track:nlp-llm
Lesson

Gates that remember: LSTM and GRU

Use gates that remember: lstm and gru to move the sequence models production brief toward a defensible release.

modality:text · algorithm:lstm · track:nlp-llm
Lesson

Many-to-one and many-to-many training

Use many-to-one and many-to-many training to move the sequence models production brief toward a defensible release.

modality:text · algorithm:lstm · track:nlp-llm
Lesson

Stateful streaming inference without future leakage

Use stateful streaming inference without future leakage to move the sequence models production brief toward a defensible release.

modality:text · algorithm:lstm · track:nlp-llm