Neural network

Q: How deeply does Designing Deep Learning Systems: A guide for software engineers cover neural network?

Defines the model’s learning role and highlights parameter-scale constraints, but defers algorithmic internals and mathematical derivations.

As explained in Designing Deep Learning Systems: A guide for software engineers

A computational model composed of interconnected parameterized units that learns mappings from inputs to outputs.

A neural network is a programmable computational model that learns from data and applies what it learns to make informed decisions. It provides the algorithmic core for deep-learning systems, while surrounding infrastructure supports development and operation. section 1.0

In a production-oriented workflow, neural networks connect to:

Deep learning and machine learning, where the network learns from data and produces decisions. section 1.0
Model prediction, inference, and model serving, which frame how a trained network is used operationally. section 1.0
Distributed training, which becomes necessary when parameter growth prevents the network from fitting on one GPU. section 4.4

Applied use cases

A chatbot uses a deep-learning model to understand user sentences and continue a conversation. An assistive-driving system uses camera images and computer vision to perceive road markings and steer. section 1.0

How Designing Deep Learning Systems: A guide for software engineers covers it

Cover of Designing Deep Learning Systems: A guide for software engineers

liveBook manning.com

Read Designing Deep Learning Systems: A guide for software engineers 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

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

Ensemble Methods for Machine LearningA neural network is a parameterized computational model composed of connected units that transform inputs through learned weights and nonlinear functions.

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 Designing Deep Learning Systems: A guide for software engineers. The section links point to the parts of the book it draws on.