Page 169 - Proceedings of the 2018 ITU Kaleidoscope

Session 6: Social, Legal and Ethical Aspects in Machine Learning
S6.1 A Gendered Perspective on Artificial Intelligence
Smriti Parsheera (National Institute of Public Finance and Policy, New Delhi, India)

Availability of vast amounts of data and corresponding advances in machine learning have brought
about a new phase in the development of artificial intelligence (AI). While recognizing the field’s
tremendous potential we must also understand and question the process of knowledgemaking in
AI. Focusing on the role of gender in AI, this paper discusses the imbalanced power structures in
AI processes and the consequences of that imbalance. We propose a three-stage pathway towards
bridging this gap. The first, is to develop a set of publicly developed standards on AI, which should
embed the concept of “fairness by design”. Second, is to invest in research and development in
formulating technological tools that can help translate the ethical principles into actual practice.
The third, and perhaps most challenging, is to strive towards reducing gendered distortions in the
underlying datasets to reduce biases and stereotypes in future AI projects.

S6.2 Ethical Framework for Machine Learning
Charru Malhotra (Indian Institute of Public Administration, India); Vinod Kotwal (Department of
Telecommunications, India); Surabhi Dalal (India Centre for Migration, India)

Artificial Intelligence (AI) with its core subset of Machine Learning (ML) is rapidly transforming
life experiences as humans begin to grow more dependent on these 'smart machines' for their needs
- ranging from routine mundane chores to critical personal decisions. However, these
transformative technologies are at the same time proving unpredictable too as has been reported
worldwide in certain cases. Therefore, several studies/reports, such as COMEST report on
Robotics ethics (UNESCO, 2017) point to an obvious need for inculcating more ethical behavior

in machines. The present study aims to look at the role and interplay of ML (the hard sciences)
and Ethics (the soft sciences) to resolve such predicaments that are inadvertently manifested by
machines not constrained or controlled by human expectations. Based on focused review of
literature of both domains-ML and Ethics, the proposed paper attempts to first build on the need
for introduction of an ethical algorithm in the domain of machine learning and then endeavors to
provide a conceptual framework to resolve the ethical dilemmas.

Undeclared Constructions: A Government's Support Deep Learning Solution for Automatic
S6.3 Change Detection

Pamela Ferrari Lezaun and Gustavo Olivieri (Universidad Tecnológica Nacional, Facultad
Regional Santa Fe, Argentina)

In our cities, in particular those with high demographic density, the proliferation of buildings goes
so fast that it is not possible or -in the best scenarios- very difficult to be handled by the government
departments regulating the legitimacy -in term of safety and taxes- of those constructions. In this
paper, we propose a deep learning tool for computer vision trained with a corpus of satellite images
provided by SpaceNet to detect changes in cities, showing the most recent constructions
automatically, which allows different municipal officers to check if they have been -or haven't
been- declared. To achieve this, we implemented the layered architecture of the SpaceNet
Challenge Round 2 winning solution, and decided to improve it with an output comparison which
gives us a high value final result for the end-user in the detection of changes, giving him the
possibility to appreciate in the graphic user interface how many new buildings and square meters
were detected.

– 153 –