How deeply does Ensemble Methods for Machine Learning cover neural network?

Explains layers, depth, induced feature combinations, and learned weights, but does not develop neural-network training internals.

Neural network

As explained in Ensemble Methods for Machine Learning

A neural network is a parameterized computational model composed of connected units that transform inputs through learned weights and nonlinear functions.

A neural network is a parameterized model that uses layers of neurons to transform inputs into increasingly complex feature combinations. Its nonlinearity grows with network depth, along with the number of weights that must be learned. This makes neural networks a flexible alternative to manually searching through combinations of nonlinear functions. section 7.1.5

For nonlinear regression, the model supports a practical workflow:

Represent the relationship between inputs and continuous labels through successive neural-network layers. section 7.1.5
Increase depth when a more complex nonlinear relationship is needed, while recognizing that additional depth introduces more weights to learn. section 7.1.5
Compare predictions with suitable regression measures such as mean squared error and mean absolute deviation. section 7.1.5

Synthetic nonlinear regression

A small data set can be generated from a damped sinusoidal function with added noise, then divided into training and test sets. Scikit-learn's MLPRegressor fits a network with three hidden layers of 50 units. On the reported test set, the neural network obtains MSE 0.043 and MAD 0.164, compared with 0.027 and 0.131 for a depth-five decision tree. section 7.1.5

How Ensemble Methods for Machine Learning covers it

Cover of Ensemble Methods for Machine Learning

liveBook manning.com

Read Ensemble Methods for Machine Learning on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Bayesian Optimization in ActionA neural network is a machine-learning model composed of interconnected computational layers that transform inputs into outputs.
liveBook manning.com

Designing Deep Learning Systems: A guide for software engineersA computational model composed of interconnected parameterized units that learns mappings from inputs to outputs.
liveBook manning.com

Demand Forecasting Best PracticesA neural network is a computational model composed of interconnected parameterized units organized in layers that transform inputs into outputs.

Compare how 4 books explain neural network →

Related concepts

deep learningused by · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
machine learningkind of · Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
autoencoderincludes · An autoencoder is a neural network that encodes input data into an internal representation and decodes it to reconstruct the input or an approximation.
recurrent neural networkincludes · A recurrent neural network is a neural network that processes sequences by updating an internal state across successive inputs, allowing earlier inputs to influence later computations.
U-Netincludes · U-Net is an encoder-decoder neural-network architecture with downsampling and upsampling paths connected by skip connections for combining features at multiple spatial scales.
gradient descentuses · Gradient descent is an iterative optimization method that updates parameters opposite the gradient of an objective function to reduce its value.

This explainer was generated by Manning's knowledge graph from the text of Ensemble Methods for Machine Learning. The section links point to the parts of the book it draws on.