Signal
A signal is an observable value, event, or pattern that conveys information about a condition, state, or phenomenon.
Outlier Detection in Python
Signal is variation in data regarded as meaningful or relevant within a particular context.
- How it is used
- Distinguishes contextually meaningful variation from noise when deciding which unusual records deserve investigation.
- How deep it goes
- Explains how engineered features expose candidate signal, but provides no standalone mathematical definition or universal signal test.
- Examples
- Uses missing-value indicators, baseball ratios, account posting summaries, and temporal features to reveal different kinds of variation.
- What you can do after
- Evaluate/understand it by choosing contextual features and checking whether flagged differences are informative rather than chance outliers.
Graph Neural Networks in Action
Information associated with an individual graph node, including attributes that can contribute to its learned representation.
- How it is used
- Uses node-specific information as input to GNN embeddings and as tabular features for non-graph baselines.
- How deep it goes
- Works through feature tensors, message passing, and distribution checks, but defers the review features’ detailed derivations.
- Examples
- Compares random and Node2Vec features in classification, and inspects normalized behavioral and textual features in a review graph.
- What you can do after
- Apply it via PyTorch Geometric by supplying node features with graph edges and inspecting feature distributions before training.
Logs and Telemetry
A signal is an observability event category encompassing logs, metrics, and traces.
- How it is used
- Groups logs, metrics, and traces for capture and distribution in an event-driven observability pipeline.
- How deep it goes
- Defines each signal and explains trace spans, nesting, baggage, and distributed relationships without detailing signal schemas.
- Examples
- Configures three OpenTelemetry inputs for logs, raw traces, and metrics, routing all matched events to standard output.
- What you can do after
- Operate/configure it through separate OpenTelemetry inputs that receive logs, traces, and metrics on designated ports.
Pro Angular 16
An Angular signal is a reactive value abstraction that represents data and tracks relationships so dependent values can update efficiently when the data changes.
- How it is used
- Describes relationships between application state and derived values so Angular can update affected HTML efficiently.
- How deep it goes
- Works through creation, reads, mutation, computed values, effects, and read-only sharing; defers deeper explanation of signal behavior.
- Examples
- Uses product-category filtering, a computed cart summary, repository state, and a route-driven product count.
- What you can do after
- Build it from scratch: create writable and computed signals, expose read-only state, and connect signal values to a template.
Financial AI in Practice
A signal is an output from an analytical model that conveys information for a subsequent financial decision or action.
- How it is used
- Positions model outputs between financial data analysis and governed decisions in trading, credit, fraud, and application workflows.
- How deep it goes
- Works through out-of-sample trading evaluation and structured news extraction, while deferring execution frictions before claims of trading profitability.
- Examples
- Uses ETF market-direction predictions and a uranium-news JSON record with sentiment, supply-risk, and policy-tone scores.
- What you can do after
- Build it from scratch using RAG-backed retrieval and structured JSON to produce auditable news features for a hybrid strategy.
Functional Design and Architecture: Examples in Haskell
A signal is a time-varying value in a functional reactive system whose changes can drive dependent computations.
- How it is used
- Frames time-dependent application state whose changes trigger reactions in functional reactive programming.
- How deep it goes
- Defines signals through time variation, dependency updates, event mapping, and bound actions without detailing an implementation.
- Examples
- Uses GUIs and complex business logic as applications for reactive networks of signals and actions.
- What you can do after
- Evaluate/understand signals as time-dependent values that automatically propagate changes to dependent computations.
Read how Functional Design and Architecture: Examples in Haskell explains signal →
Cloud Observability in Action
A signal is information about a system that can be observed externally.
- How it is used
- Uses externally observable information to understand systems and make operational decisions.
- How deep it goes
- Defines signal types, ownership, selection criteria, retention, baselines, labeling, and cost trade-offs without detailing signal implementations.
- Examples
- Demonstrates logs, metrics, and traces with a Go echo service, Grafana, Prometheus, Jaeger, curl, and load testing.
- What you can do after
- Evaluate and select signals by task relevance, actionability, retention needs, baseline value, and operational cost.
Collaborative Software Design: How to facilitate domain modeling decisions
A signal is an observable piece of information, activity, behavior, or event that indicates a change affecting a session, outcome, or result.
- How it is used
- Guides facilitators in recognizing when a group should shift between opposing poles during collaborative modeling.
- How deep it goes
- Defines strong and weak signals, explains pattern recognition, and links observations to actions without prescribing universal thresholds.
- Examples
- Uses watch-checking, confused participants, software architecture decisions, dissatisfaction, jokes, and possible team departure as signal examples.
- What you can do after
- Apply signals to observe group dynamics, detect emerging patterns, and choose actions that restore movement between polarity poles.
Optimization Algorithms: AI techniques for design, planning, and control problems
A node feature is a value or vector associated with a graph node that describes its attributes for computation or learning.
- How it is used
- Defines graph-learning problems through node features and an adjacency matrix before embedding and solution prediction.
- How deep it goes
- Places node features before GNN or GCN embedding but does not detail how to construct or encode them.
- Examples
- Uses TSP as the graph-learning task and names VRP, SAT, MaxCut, and MIS as related optimization problems.
- What you can do after
- Understand how node features enter a graph-learning pipeline for predicting combinatorial optimization solutions.
Delivering Machine Learning Projects: From design to deployment
A feature is an input variable or measurable attribute supplied to a machine learning model.
- How it is used
- Turns assembled raw data into consistent, informative model inputs before modeling.
- How deep it goes
- Explains preprocessing risks and feature representations, but stops short of detailed algorithms or implementation steps.
- Examples
- Uses year-end dates, directional values, and temperature plotted by day of year or distance from midsummer.
- What you can do after
- Apply feature engineering by planning and reviewing transformations, implementing a pipeline, and adding data augmentation.
Read how Delivering Machine Learning Projects: From design to deployment explains signal →
Related concepts
- noisecontrasts with · Noise is variation, content, or data treated as unwanted, irrelevant, or distinct from the signal, pattern, or structure of interest.
- monitoringincludes · Monitoring is the ongoing observation and measurement of a system’s behavior, state, or operational signals to assess its condition and detect changes or problems.
- toSignalproduced by · toSignal is an Angular interoperability function that creates a signal reflecting the latest value emitted by an observable.
- policy toneincludes · Policy Tone is a score representing the expressed or inferred stance and sentiment of a policy-related news source or statement.
- supply riskincludes · Supply Risk is a score representing the degree of disruption or threat to the availability of goods, inputs, or production capacity described in relevant information.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.