Deep neural networks for choice analysis: Extracting complete economic information for interpretation

Deep neural networks for choice analysis: Extracting complete economic information for interpretation

While deep neural networks (DNNs) have been increasingly applied to choice analysis showing high predictive power, it is unclear to what extent researchers can interpret economic information from DNNs. This paper demonstrates that DNNs can provide economic information as complete as classical discre...

Podrobná bibliografie
Hlavní autoři:	Wang, Shenhao, Wang, Qingyi, Zhao, Jinhua
Další autoři:	Massachusetts Institute of Technology. Department of Urban Studies and Planning
Médium:	Článek
Jazyk:	English
Vydáno:	Elsevier BV 2020
On-line přístup:	https://hdl.handle.net/1721.1/127230

Podobné jednotky

Multitask learning deep neural networks to combine revealed and stated preference data
Autor: Wang, Shenhao, a další
Vydáno: (2020)

Deep neural networks for choice analysis
Autor: Wang, Shenhao.
Vydáno: (2021)

Deep neural networks for choice analysis: Architecture design with alternative-specific utility functions
Autor: Wang, Shenhao, a další
Vydáno: (2021)

Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks
Autor: Wang, Shenhao, a další
Vydáno: (2022)

Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice models
Autor: Zheng, Yunhan, a další
Vydáno: (2022)

Uncertainty Quantification of Spatiotemporal Travel Demand With Probabilistic Graph Neural Networks
Autor: Wang, Qingyi, a další
Vydáno: (2024)

Fairness-Enhancing Deep Learning for Ride-Hailing Demand Prediction
Autor: Zheng, Yunhan, a další
Vydáno: (2024)

Deep hybrid model with satellite imagery: How to combine demand modeling and computer vision for travel behavior analysis?
Autor: Wang, Qingyi, a další
Vydáno: (2024)

An Information Theoretic Interpretation to Deep Neural Networks
Autor: Huang, Shao-Lun, a další
Vydáno: (2021)

An Information Theoretic Interpretation to Deep Neural Networks
Autor: Xu, Xiangxiang, a další
Vydáno: (2022)

Uncertainty Quantification of Sparse Trip Demand Prediction with Spatial-Temporal Graph Neural Networks
Autor: Zhuang, Dingyi, a další
Vydáno: (2022)

SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks
Autor: Zhuang, Dingyi, a další
Vydáno: (2024)

Visualizing interpretations of deep neural networks
Autor: Ta, Quynh Nga
Vydáno: (2023)

Visualizing interpretations of deep neural networks
Autor: Tan, Ryan Kang Wei
Vydáno: (2022)

Predicting drivers’ route trajectories in last-mile delivery using a pair-wise attention-based pointer neural network
Autor: Mo, Baichuan, a další
Vydáno: (2024)

Risk preference and adoption of autonomous vehicles
Autor: Wang, Shenhao, a další
Vydáno: (2020)

Interpretation of trained neural networks by rule extraction
Autor: Palade, V, a další
Vydáno: (2001)

Modular learning of convolutional neural networks
Autor: Wang, Jinhua
Vydáno: (2023)

HyDRA: hypergradient data relevance analysis for interpreting deep neural networks.
Autor: Chen, Yuanyuan, a další
Vydáno: (2021)

Data-Driven Vehicle Rebalancing With Predictive Prescriptions in the Ride-Hailing System
Autor: Guo, Xiaotong, a další
Vydáno: (2024)

Behavioral and neural signatures of information sampling to guide economic choice
Autor: Kaanders, P
Vydáno: (2022)

Information extraction with neural networks
Autor: Lee, Ji Young, Ph. D. Massachusetts Institute of Technology
Vydáno: (2017)

What prompts the adoption of car restriction policies among Chinese cities
Autor: Wang, Shenhao, a další
Vydáno: (2020)

Deep neural open information extraction with background knowledge
Autor: Mtumbuka, FM
Vydáno: (2022)

Model extraction attack on Deep Neural Networks
Autor: Lkhagvadorj, Dulguun
Vydáno: (2022)

Interpreting Deep Learning-Based Networking Systems
Autor: Meng, Zili, a další
Vydáno: (2022)

Measuring policy leakage of Beijing’s car ownership restriction
Autor: Zheng, Yunhan, a další
Vydáno: (2022)

Estimating Information Flow in Deep Neural Networks
Autor: Goldfeld, Ziv, a další
Vydáno: (2021)

Theoretical Insights into Neural Networks and Deep Learning: Advancing Understanding, Interpretability, and Generalization
Autor: Usmani, Usman Ahmad, a další
Vydáno: (2023)

Interpretable fuzzy-embedded deep neural network with its application in stock trading
Autor: Koh, Amadeus Ying Jie
Vydáno: (2023)

The relationship between ridehailing and public transit in Chicago: A comparison before and after COVID-19
Autor: Meredith-Karam, Patrick, a další
Vydáno: (2024)

Safety verification of deep neural networks
Autor: Huang, X, a další
Vydáno: (2017)

Fingerprinting deep neural networks - a DeepFool approach
Autor: Wang, Si, a další
Vydáno: (2021)

Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice models
Autor: Zheng, Yunhan
Vydáno: (2022)

Trading the fundamentals : the trader's complete guide to interpreting economic indicators and monetary policy /
Autor: 295419 Niemira, Michael P., a další
Vydáno: (1994)

Automated Mechanistic Interpretability for Neural Networks
Autor: Liao, Isaac C.
Vydáno: (2024)

Monetary policy information extraction from open sources based on deep neural networks and natural language processing
Autor: Xue, Zixian
Vydáno: (2022)

Understanding neural network sample complexity and interpretable convergence-guaranteed deep learning with polynomial regression
Autor: Emschwiller, Matt V.
Vydáno: (2020)

Evolving data-driven Interpretable fuzzy deep neural network (IFDNN) with applications in algorithmic finance
Autor: Kan, Nicole Hui Lin
Vydáno: (2022)

Attention graph neural network on heterogeneous information network
Autor: Wang, Kexin
Vydáno: (2020)