The Dictionary

Two corpora, one search. The vocabulary of AI and mathematics on one side, the working language of software engineering on the other — every term defined so it can be substituted back into a sentence, and every claim pointed at the paper it came from.

21 AI & Mathematics18 Software Engineering Core39 entries total

"exact phrase" · *ology wildcard · tensor NOT physics · misspellings are corrected automatically

Search

AI & Mathematics

The vocabulary of machine learning, statistics, optimisation and the linear algebra underneath all of it. Every entry is defined in terms a reader can substitute back into a sentence, then anchored to the paper or theorem it came from.

21 entries
Neural Networks AIM-00022

Activation Function

noun

a mathematical function that introduces non-linearity into the output of a layer, allowing the network to learn complex patterns.

CoreFoundational
Deep Learning AIM-00005

Attention Mechanism

noun

a layer that produces each output as a weighted blend of all available inputs, where the weights are computed from the similarity between a query and a set of keys.

Core
Neural Networks AIM-00002

Backpropagation

noun

an application of the chain rule that computes the sensitivity of a loss to every parameter in a layered network by passing partial derivatives from the output back toward the input.

CoreFoundational
Probability AIM-00006

Bayes' Theorem

noun

the identity that converts the likelihood of evidence given a hypothesis into the probability of the hypothesis given that evidence, by weighting it with the hypothesis's prior probability.

CoreFoundational
Statistical Learning AIM-00018

Bias-Variance Tradeoff

noun

the fundamental tension between the complexity of a model and its ability to generalize to unseen data.

CoreFoundational
Deep Learning AIM-00010

Convolutional Neural Network

noun

an architecture that slides a small set of learned filters across grid-structured input, so the same local pattern is recognised wherever it appears and far fewer weights are needed than a fully connected design.

Core
Model Evaluation AIM-00012

Cross-Validation

noun

a technique used to estimate the performance of a model on unseen data by partitioning the dataset into multiple subsets.

CoreFoundational
Linear Algebra AIM-00004

Eigenvector

noun

a non-zero vector whose direction is unchanged by a given linear map, so the map merely rescales it by a constant factor.

CoreFoundational
Representation Learning AIM-00016

Embedding

noun

a low-dimensional vector representation of high-dimensional data, such as words or images, that captures semantic or structural relationships.

CoreFoundational
Information Theory AIM-00013

Entropy

noun

a measure of the uncertainty or randomness inherent in a random variable or source of data.

CoreFoundational
Optimization AIM-00001

Gradient Descent

noun

an iterative procedure that reduces a differentiable objective by repeatedly stepping in the direction opposite to its slope at the current point.

CoreFoundational
Optimization AIM-00008

Learning Rate

noun

a hyperparameter that controls the step size taken at each iteration of an optimization algorithm.

CoreFoundational
Optimization AIM-00007

Loss Function

noun

a measure of the difference between predicted and actual values, quantifying the error of a model's output.

CoreFoundational
Probability AIM-00014

Markov Chain

noun

a sequence of random variables where the probability of transitioning to the next state depends only on the current state, and not on the sequence of states that preceded it.

CoreFoundational
Statistics AIM-00020

Maximum Likelihood Estimation

noun

a method that picks the parameter values under which the observed data would have been most probable, by maximising the probability the model assigns to that data.

CoreFoundational
Statistical Learning AIM-00003

Overfitting

noun

the failure mode in which a model absorbs noise particular to its training sample and therefore predicts unseen data worse than a simpler model would.

Core
Dimensionality Reduction AIM-00019

Principal Component Analysis

noun

a transformation that rewrites correlated measurements as a smaller set of uncorrelated axes, ordered so the first captures as much of the spread as any single direction can.

Core
Statistical Learning AIM-00009

Regularization

noun

a technique used to prevent overfitting by adding a penalty term to the loss function, which discourages overly complex models.

CoreFoundational
Machine Learning AIM-00017

Reinforcement Learning

noun

a training paradigm in which an agent improves its policy purely from rewards collected while acting in an environment, with no labelled examples of correct behaviour to imitate.

Core
Deep Learning AIM-00011

Softmax

noun

a function that takes a vector of real numbers and maps it to a probability distribution, ensuring that all elements are positive and sum to one.

Core
Deep Learning AIM-00015

Transformer

noun

a neural network architecture that relies solely on attention mechanisms, allowing it to process sequential data efficiently.

CoreFoundational

Software Engineering Core

The working vocabulary of building and running software — algorithms, architecture, concurrency, databases, security and the field's durable jargon. Definitions are written to be substitutable, and the idioms carry the origin story only where it is actually documented.

18 entries
Databases SWE-00019

ACID

abbreviation

the guarantee that a group of statements either takes effect entirely or not at all, never observes a partial state, does not interfere with concurrent work, and survives a crash once confirmed.

CoreAcronym
Algorithms SWE-00007

Big O Notation

noun

a way of describing how the cost of an algorithm grows as its input grows, keeping only the dominant term and discarding constants.

CoreFoundational
Distributed Systems SWE-00032

CAP Theorem

noun

the result that when a network splits, a replicated store must give up either answering every request or returning the newest written value — it cannot preserve both.

CoreAcronym
Architecture SWE-00016

Cohesion

noun

the degree to which the parts of a single module all serve one purpose, rather than being grouped together for incidental reasons.

Core
Architecture SWE-00015

Coupling

noun

the degree to which one module depends on the internals of another, and therefore how far a change in one propagates into the other.

Core
Concurrency SWE-00004

Deadlock

noun

a state in which two or more processes are each waiting for the other to release a resource, resulting in a permanent halt of execution.

CoreFoundational
Architecture SWE-00013

Dependency Injection

noun

the practice of supplying a component's collaborators from outside rather than letting it construct them, so the component can be reconfigured or tested without being modified.

Core
Distributed Systems SWE-00031

Eventual Consistency

noun

the guarantee that if updates stop arriving, every replica will converge on the same values — with no promise about what a reader sees before then.

Core
Data Structures SWE-00008

Hash Table

noun

a container that converts each key into an array position by arithmetic, giving constant-time average lookup at the cost of handling positions that collide.

CoreFoundational
API Design SWE-00002

Idempotence

noun

the property of an operation whose repeated application produces the same result as a single application, so a retry cannot cause additional change.

Core
Algorithms SWE-00006

Memoization

noun

the technique of storing the results of expensive function calls and returning the cached result when the same inputs occur again.

CoreOptimization
Concurrency SWE-00005

Mutex

noun

a synchronization primitive used to ensure that only one thread can access a shared resource at any given time.

CoreFoundational
Programming Paradigms SWE-00040

Pure Function

noun

a routine whose result is determined entirely by its arguments and which changes nothing outside itself, so calling it twice with the same input is indistinguishable from calling it once.

Core
Concurrency SWE-00003

Race Condition

noun

a defect in which the correctness of a result depends on the unpredictable relative timing of two or more independent threads of execution.

Core
Craft SWE-00035

Refactoring

noun

a change to the internal structure of existing code that leaves its observable behaviour exactly as it was, undertaken to make later changes cheaper.

Core
Security SWE-00023

SQL Injection

noun

an attack in which text supplied by a user is concatenated into a database query and thereby executed as part of the command rather than treated as a value.

CoreVulnerability
Craft SWE-00001

Technical Debt

noun

the future cost incurred by choosing an expedient implementation now instead of a sounder one, paid back as extra effort on every later change.

CoreMetaphor
Jargon SWE-00047

Yak Shaving

noun

the state of working through a chain of unplanned prerequisite tasks, each apparently necessary for the last, so far from the original goal that the connection is no longer obvious.

JargonIdiom