Concepts · Definitions · Insights · Interview Prep
Transformers, LLMs, RAG, Agents, and the generative AI stack
Classical ML, deep learning, training patterns, and foundations
Data engineering, pipelines, and data-centric AI
Linear algebra, calculus, probability for ML
A systematic evaluation process where individual components of a machine learning model are removed to measure their exact contribution to performance.
Analogy: Like removing ingredients from a recipe one by one to figure out exactly which spice is making the soup taste good.
Related: Feature Importance, Model Pruning, Association Rule Mining
A mathematical operation applied to a neural network node's output that introduces the crucial non-linearity required to learn highly complex patterns.
Analogy: Like a gatekeeper deciding how loudly a message should be shouted to the next room based on the importance of the incoming signal.
An interpretability technique that proves a network component handles a specific concept by pasting its clean activations into a corrupted forward pass and w...
Analogy: Like bypassing a broken house fuse with a battery to prove that specific fuse controls the kitchen lights.
Related: Sparse Autoencoder, Ablation Study, Agent Harness
Read the full conceptA specialized training paradigm where the model explicitly selects the most informative unlabelled data points and queries a human annotator for labels.
Analogy: Like a student who only asks the teacher for help on the hardest questions they don't understand, rather than asking about everything in the textbook.
Related: Human-in-the-Loop, Semi-Supervised Learning, CTC Loss
An incredibly popular adaptive optimization algorithm that combines momentum and scaling to dynamically adjust the learning rate of individual parameters.
Analogy: Like a driver who remembers their past speed (momentum) while adapting to the current road conditions (scaling) for each individual tire.
Related: Learning Rate Scheduling, Second-Order Optimization, Batch Normalization
A tiny set of highly trainable parameters injected into the layers of a frozen, pre-trained neural network to drastically simplify task-specific tuning.
Analogy: Like adding a custom optical filter to the front of an expensive camera lens instead of rebuilding the entire lens from scratch.
Related: PEFT, Foundation Model, Bias (parameter)
AI safety isn't just philosophical debates. It is guardrails, red teaming, and why a system prompt isn't enough.
SageMaker is huge, expensive, and powerful. Here is when you actually need it, and when you are just burning money.
Quick answer
Multimodal LLMs project disparate data types (like pixels and audio waveforms) into a shared continuous embedding space, allowing a single transformer architecture to process them alongside text tokens.
Quick answer
By employing data masking/redaction before sending prompts to the LLM, using zero-data retention policies with model providers, or deploying open-weights models locally to ensure data never leaves the corporate boundary.
Quick answer
Monitoring requires logging end-to-end traces, tracking cost and latency metrics, tracking explicit user feedback (thumbs up/down), and sampling production data with LLM-as-a-judge pipelines to detect behavioral drift over time.
Explore our full library of concepts, definitions, and tutorials. Let's build something amazing.