Fully connected neural network
A fully connected neural network is a neural network whose units in each layer connect to every unit in the adjacent layer.
Deep Learning with R, Third Edition
A dense neural network is a neural network architecture in which units in one layer are connected to all units in the adjacent layer.
- How it is used
- Processes vector or structured data and commonly forms final classification or regression stages.
- How deep it goes
- Defines all-to-all adjacent-layer connections, contrasts local convolution, and demonstrates practical classification and regression configurations.
- Examples
- Uses California housing, Jena temperature forecasting, and compact Keras models for binary, categorical, multilabel, and regression tasks.
- What you can do after
- Build it from scratch in R/Keras by selecting Dense layers, output activations, losses, optimizers, metrics, and evaluation procedures.
Read how Deep Learning with R, Third Edition explains fully connected neural network →
Grokking Machine Learning
A neural-network layer in which each unit receives input from all units in the preceding layer.
- How it is used
- Classifies handwritten digits and a circular two-class dataset with small neural networks.
- How deep it goes
- Demonstrates network architectures, training, and testing evaluation, then notes where flattened-image inputs fall short.
- Examples
- Uses MNIST digit images, a circular binary dataset, and a 3 misclassified as an 8.
- What you can do after
- Apply TensorFlow Keras to train a small classifier and evaluate its predictions on test data.
Read how Grokking Machine Learning explains fully connected neural network →
Machines that Think
A dense network is a neural network whose units are broadly connected between adjacent layers without specialized exploitation of spatial or sequential structure.
- How it is used
- Frames dense networks as flexible models whose missing structural assumptions motivate specialized architectures.
- How deep it goes
- Defines layer-to-layer connectivity and explains structural limitations, but does not detail implementation or training mechanics.
- Examples
- Uses flattened images, unordered sentence inputs, and time series without temporal rhythm to illustrate lost structure.
- What you can do after
- Evaluate whether dense networks suit data whose spatial, sequential, or temporal patterns require architectural support.
Read how Machines that Think explains fully connected neural network →
Also covered in
- Fight Fraud with Machine LearningIn early access (MEAP)
- Time Series Forecasting Using Foundation Models
What to know first
- convolutional neural networkA convolutional neural network is a neural-network architecture that processes structured inputs with convolutional operations, typically using learned local filters to capture patterns.
Related concepts
- N-BEATSused by · N-BEATS is a neural forecasting model organized as stacks of blocks for modeling time series without requiring explicit series decomposition or input transformations.
- deep learningkind of · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
- linear layerhas part · A linear layer is a neural-network layer that applies a learned affine transformation to its input, typically using weights and a bias.
- recurrent neural networkcontrasts with · A recurrent neural network is a neural network that processes ordered inputs while carrying and updating an internal state across successive steps.
- neural networkkind of · A neural network is a computational model composed of interconnected, parameterized units or transformations that learn to map inputs to outputs.
Questions about fully connected neural network
What is fully connected neural network?
A fully connected neural network is a neural network whose units in each layer connect to every unit in the adjacent layer.
Which Manning books explain fully connected neural network?
Deep Learning with R, Third Edition, Grokking Machine Learning and Machines that Think.
What should I know before learning fully connected neural network?
Manning books that teach fully connected neural network usually introduce convolutional neural network first.
What is the difference between fully connected neural network and recurrent neural network?
A fully connected neural network is a neural network whose units in each layer connect to every unit in the adjacent layer. A recurrent neural network is a neural network that processes ordered inputs while carrying and updating an internal state across successive steps.
What is fully connected neural network a kind of?
Fully connected neural network is a kind of deep learning. Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
What is fully connected neural network part of?
Fully connected neural network is part of block. A block is an N-BEATS computational subunit that produces a prediction and a backcast representing information captured from its input.
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.


