£73.39

Discrete Latent Structure in Neural Networks (Foundations and Trends® in Engineering)

AI & Machine Learning

Price data last checked 44 day(s) ago - refreshing...

View at Amazon

We'll watch every seller, every day. One email when your price arrives.

This is the most expensive it has ever been. Walk away.

£73 today · previous high £73 · all-time low £64

NEW HERE?

Amazon shows you one price. We show you all of them.

Tosheroon watches Amazon prices so you don't have to. Every product on Amazon has a price history — we make it visible. Set the price you'd actually pay, and we'll email you the second it gets there. No app, no account, one email.

WHAT'S ON THIS PAGE

↓ Price chart
when this has been cheap or pricey

↓ Forecast
where the price is heading next

↓ Statistics
all-time high & low, recent range

↑ Price alert
name your number, we'll email you

Price History & Forecast

Grey patches = out of stock. Cheaper = lower on the chart. Hover for exact prices.

Last 47 days · 47 data points (no recent data)

Historical

Generating forecast…

Price Distribution

Price distribution over 47 days • 2 price levels

Days at Price

Current Price

Price Analysis

Most common price: £64 (45 days, 95.7%)

Price range: £64 - £73

Price levels: 2 different prices over 47 days

Description

Machine learning (ML) is often employed to build predictive models for analyzing rich data, such as images, text, or sound. Most such data is governed by underlying structured representations, such as segmentations, hierarchy, or graph structure. It is common for practical ML systems to be structured as pipelines, including off-the-shelf components that produce structured representations of the input, used as features in subsequent steps of the pipeline. On the one hand, such architectures require availability of these components, or of the data to train them. Since the component may not be built with the downstream goal in mind, a disadvantage of pipelines is that they are prone to error propagation. On the other hand, they are transparent: the predicted structures can be directly inspected and used to interpret downstream predictions. In contrast, deep neural networks rival and even outperform pipelines by learning dense, continuous representations of the data, solely driven by the downstream objective. This monograph is about neural network models that induce discrete latent structure, combining the strengths of both end-to-end and pipeline systems. In doing so, not one specific downstream application in natural language processing nor computer vision is assumed, however the presentation follows an abstract framework that allows to focus on technical aspects related to end-to-end learning with deep neural networks. The text explores three broad strategies for learning with discrete latent structure: continuous relaxation, surrogate gradients, and probabilistic estimation. The presentation relies on consistent notations for a wide range of models. As such, many new connections between latent structure learning strategies are revealed, showing how most consist of the same small set of fundamental building blocks, but use them differently, leading to substantially different applicability and properties.

Product Specifications

Format: paperback
ASIN: 1638285705
Category: Books > Subjects > Computing & Internet > Computer Science > AI & Machine Learning
Domain: Amazon UK
Release Date: 02 June 2025
Listed Since: 09 June 2025

Barcode

No barcode data available

Discrete Latent Structure in Neural Networks (Foundations and Trends® in Engineering)

This is the most expensive it has ever been. Walk away.

Price History & Forecast

Price Distribution

Price Analysis

Description

Product Specifications

Barcode

Similar Products You Might Like

Harnessing the Potential of Deep-learning Algorithms and Generative AI for SoC and Chiplet Design and Verification (Foundations and Trends® in Engineering)

FUNDAMENTALS OF ENGINEERING SCIENCE AND TECHNOLOGY

Artificial Neural Networks: Alpha Unpredictability and Chaotic Dynamics

The Fundamentals of Metal-Matrix Composites (Materials Science and Technologies)

Network Coding for Engineers

Machine Learning and Deep Learning Meet Computer Networks

Efficient Nonlinear Adaptive Filters: Design, Analysis and Applications

Neural Dynamics for Time-varying Problems: Advances and Applications

Research in Novel Materials (Materials Science and Technologies)

The Dentate Gyrus: Structure, Functions and Health Implications (Neuroscience Research Progress)

Frontiers in Optical Technology

Introduction to Engineering Computation: Programming and Numerical Methods in MATLAB

Reinforcement Learning in Action: From Foundations to Frontier AI

Fundamentals of Structural Engineering: A Problem-Based Approach

Analog Current-Mode Computational Circuits for Artificial Neural Networks (Analog Circuits and Signal Processing)

Fault Detection: Methods, Applications & Technology (Systems Engineering Methods, Developments and Technology)

Hydrocephalus: From Diagnosis to Treatment (Neurology - Laboratory and Clinical Research Developments)

Structural Principles of Wireless Networks

Innovations in Real-Time Machine Learning: Navigating Dynamic Dataset

Computational Techniques in Neuroscience (Computational Methods for Industrial Applications)

Discrete Dynamics: Basic Theory and Examples (Mathematical Engineering)

Fundamentals of Electromigration-Aware Integrated Circuit Design

A Closer Look at Glycation (Biochemistry Research Trends)

Gauge Theories & Differential Geometry (Physics Research and Technology: Mathematics Research Developments)