12 research outputs found
Universality out of order
No full textFunding Information: The author thanks Gourab Ghoshal for comments and acknowledges financial support from JSPS KAKENHI grant no. JP21H04595.Peer reviewe
Fairness in agreement with European values: An interdisciplinary perspective on ai regulation
No full textWith increasing digitalization, Artificial Intelligence (AI) is becoming ubiquitous. AI-based systems to identify, optimize, automate, and scale solutions to complex economic and societal problems are being proposed and implemented. This has motivated regulation efforts, including the Proposal of an EU AI Act. This interdisciplinary position paper considers various concerns surrounding fairness and discrimination in AI, and discusses how AI regulations address them, focusing on (but not limited to) the Proposal. We first look at AI and fairness through the lenses of law, (AI) industry, sociotechnology, and (moral) philosophy, and present various perspectives. Then, we map these perspectives along three axes of interests: (i) Standardization vs. Localization, (ii) Utilitarianism vs. Egalitarianism, and (iii) Consequential vs. Deontological ethics which leads us to identify a pattern of common arguments and tensions between these axes. Positioning the discussion within the axes of interest and with a focus on reconciling the key tensions, we identify and propose the roles AI Regulation should take to make the endeavor of the AI Act a success in terms of AI fairness concerns. Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Web Information System
Towards Safety and Sustainability: Designing Local Recommendations for Post-pandemic World
No full textExtended Version of The Paper:
Towards_Safety_and_Sustainability_Extended.pdf
Dataset Information:
List of files
Customer_Choice_Survey.csv
NYC_Google.csv
NYC_Yelp.csv
SF_Google.csv
SF_Yelp.csv
Field Details in Each File
"Customer_Choice_Survey.csv": Local recommendations received on Google Local (Google Maps) for different customer locations in New York and San Francisco.
Each respondent was first asked some basic details.
Then 7 rounds of ranking questions were asked.
In each round, they were given a list of 10 restaurants with random combinations of rating, distance and cuisine. They were asked to rank top 5 one-by-one out of those 10 provided. This becomes evident from the question titles provided the file.
"NYC_Google.csv" and "SF_Google.csv": Local recommendations received on Yelp for different customer locations in New York and San Francisco.
"customer_location": location of the customer where she gets recommendation
"rank": rank of the restaurant in the recommended list
"id": restaurant's id internal to google
"latitude": latitude of restaurant's geographic coordinates
"longitude": longitude of restaurant's geographic coordinates
"name": name of the resturant
"price_level": cheap/costly level
"rating": average rating of the restaurant
"rating_count": number of ratings collected for the restaurant
"address": address of the restaurant
"NYC_Yelp.csv" and "SF_Yelp.csv"
"customer_location": location of the customer where she gets recommendation
"rank": rank of the restaurant in the recommended list
"id": restaurant's id internal to yelp
"latitude": latitude of restaurant's geographic coordinates
"longitude": longitude of restaurant's geographic coordinates
"name": name of the resturant
"rating": average rating of the restaurant
"rating_count": number of ratings collected for the restaurant
"address": address of the restaurant
"url": link to the restaurant's yelp page
Link to Code Repository:
Pandemic-Aware Local Recommendation
Citation Information:
Please cite the following paper if you use this dataset.
"Towards Sustainability and Safety: Designing Local Recommendations for Post-pandemic World"
Gourab K Patro, Abhijnan Chakraborty, Ashmi Banerjee, Niloy Ganguly.
In proceedings of Fourteenth ACM Conference on Recommender Systems (RecSys-2020), Virtual Event, Brazil.
You can also use the following bibtex.
@inproceedings{10.1145/3383313.3412251,
author = {Patro, Gourab K and Chakraborty, Abhijnan and Banerjee, Ashmi and Ganguly, Niloy},
title = {Towards Safety and Sustainability: Designing Local Recommendations for Post-Pandemic World},
year = {2020},
isbn = {9781450375832},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3383313.3412251},
doi = {10.1145/3383313.3412251},
booktitle = {Fourteenth ACM Conference on Recommender Systems},
pages = {358–367},
numpages = {10},
keywords = {COVID-19, Local Recommendation, Google Local, Yelp, Safety, Social Distancing, Sustainability, Bipartite Matching},
location = {Virtual Event, Brazil},
series = {RecSys '20}
Focusing of Ultrasound for Photo-Acoustic Subsurface Imaging in AFM Cantilever tip
No full textOver the past few years, sub-surface imaging techniques at the nano-scale have become increasingly important in the semiconductor industry, whereby voids, cracks and other heterogenous features can be detected using disturbances in penetrating waves inside the substrate. A certain modality called photo-acoustic subsurface Atomic Force Microscopy (passAFM) is currently in development at the DMN group in TU Delft. PassAFM uses two fs pulsed lasers to generate and detect acoustic waves inside an AFM cantilever. This technique promises a lateral resolution of subsurface imaging in the order of the AFM tip size. It is required to focus the acoustic waves inside the tip and obtain sufficient acoustic power to detect a signal back from the tip. Therefore, acoustic lensing devices are designed and the improvement in detected signal is studied in this research.Mechanical Engineering | High-Tech Engineerin
Recommended from our members
International arbitration and the rule of law ::essays in honour of Fali Nariman /
No full textThis volume seeks to commemorate the contribution of Mr. Fali S. Nariman to international arbitration. Mr. Nariman spearheaded the organisation of the Permanent Court of Arbitration India Conferences that took place in Delhi in October 2017 and October 2018 and were jointly organised by the PCA and the Indian Ministry of External Affairs. The articles in this volume are a collection of the contributions made at these conferences. The volume contains 30 contributions covering current issues in interstate dispute settlement, investor-State dispute resolution, and international commercial arbitration
A characterisation of the Gaussian free field
No full textWe prove that a random distribution in two dimensions which is conformally invariant and satisfies a natural domain Markov property is a multiple of the Gaussian free field. This result holds subject only to a fourth moment assumption.© The Author(s) 201
Drivers’ Ability to Distinguish Consecutive Horizontal Curves
No full textDriver error in distinguishing preceding and upcoming horizontal curves can lead to single-vehicle fatal crashes. The 3-D perspective views of different horizontal curve stimuli were used to examine a representative sample of volunteering drivers’ ability to distinguish consecutive horizontal curves. A probit model, developed using the recorded responses, revealed that differences in radius and deflection angle between the consecutive curves are more likely to influence, whereas radius and deflection angle of reference curve is less likely to influence drivers in distinguishing consecutive curve. The sensitivity analysis of the model parameters indicated a difference in radius between the consecutive curves as the most and deflection angle of reference curve as the least sensitive parameters. The estimated marginal effects are useful for evaluating the design and safety of consecutive curves from the drivers’ perspective. Finally, nomograms were developed for relevant applications.The presentation of the authors' names and (or) special characters in the title of the pdf file of the accepted manuscript may differ slightly from what is displayed on the item page. The information in the pdf file of the accepted manuscript reflects the original submission by the author
Nonparametric Empirical Bayes Estimation on Heterogeneous Data
No full textThe simultaneous estimation of many parameters based on data collected from
corresponding studies is a key research problem that has received renewed
attention in the high-dimensional setting. Many practical situations involve
heterogeneous data where heterogeneity is captured by a nuisance parameter.
Effectively pooling information across samples while correctly accounting for
heterogeneity presents a significant challenge in large-scale estimation
problems. We address this issue by introducing the ``Nonparametric Empirical
Bayes Structural Tweedie" (NEST) estimator, which efficiently estimates the
unknown effect sizes and properly adjusts for heterogeneity via a generalized
version of Tweedie's formula. For the normal means problem, NEST simultaneously
handles the two main selection biases introduced by heterogeneity: one, the
selection bias in the mean, which cannot be effectively corrected without also
correcting for, two, selection bias in the variance. We develop theory to show
that NEST is asymptotically as good as the optimal Bayes rule that uniquely
minimizes a weighted squared error loss. In our simulation studies NEST
outperforms competing methods, with much efficiency gains in many settings. The
proposed method is demonstrated on estimating the batting averages of baseball
players and Sharpe ratios of mutual fund returns. Extensions to other members
of the two-parameter exponential family are discussed.Comment: Citations corrected and a new author added. No change in content
