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
Any optimizer that gives each parameter its own effective learning rate from that parameter's own gradient history, rather than one shared rate for all of them.
Related: Second-Order Optimization, Gradient, Convex Function
Read the full conceptA square grid recording which pairs of nodes in a graph are connected, with one row and one column per node.
Related: Matrix, Sparse Matrix, Matrix Rank
Read the full conceptRepresenting a document as counts over a fixed vocabulary, discarding word order entirely.
Related: TF-IDF, Tokenization, Sparse Matrix
Read the full conceptHow the number of examples averaged into one gradient estimate changes training noise, the largest stable learning rate, and final generalization.
Related: Gradient Accumulation, Learning Rate Scheduling, Gradient
Read the full conceptThe rule for updating a belief after seeing evidence, by combining how well the evidence fits with how plausible the belief was beforehand.
Related: Likelihood, Random Variable
Read the full conceptThe number of distinct values a column contains — two for a yes/no flag, fifty thousand for a merchant ID.
Related: One-Hot Encoding, Hashing Trick, Feature
Read the full concept
Article 50 of the EU AI Act requires disclosing AI-generated content and chatbot interactions starting 2 August 2026. The obligation is simple to state and easy to implement wrong at the boundary cases.
Every narrow-format announcement leads with a throughput multiple. The number is real. What it leaves out is that you are buying it with dynamic range, and the bill arrives as a NaN four hundred steps into a run.
Quick answer
Choose L1 when you want feature selection — it drives coefficients to exactly zero because its unit ball has corners on the axes. Choose L2 for smooth shrinkage and easier optimisation.
Quick answer
Variance measures how far one variable scatters from its own mean. Covariance measures whether two variables are unusual at the same time. Variance is the special case where a variable covaries with itself.
Quick answer
It tells you how many axes there are and how long each one is. It does not tell you what any axis means — that agreement lives only in your code, which is why a wrong axis gives a wrong answer rather than an error.
Explore our full library of concepts, definitions, and tutorials. Let's build something amazing.