Perceptron
A perceptron is a single-layer computational model and linear classifier that combines weighted inputs with a bias and applies a threshold or activation rule.
Grokking Machine Learning
A processing unit or model that computes a weighted combination of inputs, adds a bias, and applies an activation function.
- How it is used
- Predicts one of two categories from features, using sentiment analysis as the running classification problem.
- How deep it goes
- Works through scores, boundaries, and iterative corrections; also identifies gradient descent as another training route.
- Examples
- Uses word counts and alien moods to draw a boundary, then names spam filtering and recommendations as applications.
- What you can do after
- Build it from scratch by scoring features, applying a step function, and repeatedly correcting misclassified points.
Math and Architectures of Deep Learning
A simple linear threshold unit that computes a weighted sum of inputs.
- How it is used
- Models binary classification and supplies the repeated threshold unit from which multilayer neural networks are built.
- How deep it goes
- Derives threshold geometry, logic-gate constructions, multilayer combinations, and a matrix-based PyTorch implementation; defers parameter training to gradient-based methods.
- Examples
- Uses AND, OR, NOT, XOR, planar and polygonal decision regions, plus PyTorch threshold-unit code.
- What you can do after
- Evaluate/understand when one thresholded linear unit can classify data and why multilayer networks are needed for nonlinearly separable functions.
Read how Math and Architectures of Deep Learning explains perceptron →
Natural Language Processing in Action, Second Edition
A perceptron is a single-layer computational model that computes a weighted sum of inputs and applies a thresholding activation to make a decision.
- How it is used
- Uses a single artificial neuron to turn numerical features into a decision, including decisions based on text features.
- How deep it goes
- Works through weights, an intercept, and step or logistic activation in Python, but leaves weight training at a conceptual level.
- Examples
- Calculates a weighted sum from word counts and applies perceptrons to predicting birth-certificate sex labels from first names.
- What you can do after
- Build it from scratch as a Python feed-forward neuron that weights inputs and applies a threshold.
Read how Natural Language Processing in Action, Second Edition explains perceptron →
Grokking AI Algorithms, Second Edition
A perceptron is a computational unit and binary linear classifier that combines weighted inputs with a bias and applies an activation rule.
- How it is used
- Uses a neuron-inspired unit to turn weighted inputs into a prediction for a simple classification problem.
- How deep it goes
- Traces inputs through weights, summation, and activation, but defers how training adjusts the weights.
- Examples
- Illustrates prediction with apartment size and price, then contrasts a multi-input car-collision neural network.
- What you can do after
- Evaluate/understand how an already-trained perceptron combines inputs into an output and when multiple hidden nodes may be more suitable.
Read how Grokking AI Algorithms, Second Edition explains perceptron →
Machine Learning Algorithms in Depth
A linear binary classifier that predicts a class from the sign of a weighted sum of input features.
- How it is used
- Introduces supervised classification through a linear binary classifier trained by correcting mistakes.
- How deep it goes
- Derives the prediction rule and decision-boundary geometry, then gives a from-scratch training implementation and evaluation measures.
- Examples
- Uses iris binary classification, a two-dimensional decision-boundary figure, implementation pseudocode, and a confusion matrix.
- What you can do after
- Build it from scratch and evaluate its binary predictions with a confusion matrix.
Read how Machine Learning Algorithms in Depth explains perceptron →
Related concepts
- classifierkind of · A classifier is a predictive computational model that assigns inputs to one or more discrete classes or categories.
- neuronkind of · A neuron is a computational unit in a neural network that transforms inputs, typically using learned parameters and an activation function, to produce an output.
- step functionuses · A step function is a piecewise-constant function that changes abruptly between discrete output values when its input crosses one or more specified thresholds.
- language modelpart of · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- logical AND operatorimplements · A logical AND operator is a Boolean conjunction that produces true exactly when all operands have true truth values.
- logistic regressioncontrasts with · Logistic regression is a statistical classification model that estimates categorical outcome probabilities by applying a logistic or softmax function to a linear combination of input features.
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.