Search and recommendation systems, such as search engines, recruiting tools, online marketplaces, news, and social media, output ranked lists of content, products, and sometimes, people. Credit ratings, standardized tests, risk assessments output only a score, but are also used implicitly for ranking. Bias in such ranking systems, especially among the top ranks, can worsen social and economic inequalities, polarize opinions, and reinforce stereotypes. On the other hand, a bias correction for minority groups can cause more harm if perceived as favoring group-fair outcomes over meritocracy. In this paper, we study a trade-off between individual fairness and group fairness in ranking. We define individual fairness based on how close the predicted rank of each item is to its true rank, and prove a lower bound on the trade-off achievable for simultaneous individual and group fairness in ranking. We give a fair ranking algorithm that takes any given ranking and outputs another ranking with simultaneous individual and group fairness guarantees comparable to the lower bound we prove. Our algorithm can be used to both pre-process training data as well as post-process the output of existing ranking algorithms. Our experimental results show that our algorithm performs better than the state-of-the-art fair learning to rank and fair post-processing baselines.

An enormous and ever-growing volume of data is nowadays becoming available in a sequential fashion in various real-world applications. Learning in nonstationary environments constitutes a major challenge, and this problem becomes orders of magnitude more complex in the presence of class imbalance. We provide new insights into learning from nonstationary and imbalanced data in online learning, a largely unexplored area. We propose the novel Adaptive REBAlancing (AREBA) algorithm that selectively includes in the training set a subset of the majority and minority examples that appeared so far, while at its heart lies an adaptive mechanism to continually maintain the class balance between the selected examples. We compare AREBA with strong baselines and other state-of-the-art algorithms and perform extensive experimental work in scenarios with various class imbalance rates and different concept drift types on both synthetic and real-world data. AREBA significantly outperforms the rest with respect to both learning speed and learning quality. Our code is made publicly available to the scientific community.

As the size of the NLP model increases into the hundreds of billions of parameters, so does the importance of being able to create more compact representations of these models. Knowledge distillation has successfully enabled this but is still considered an afterthought when designing the teacher models. This probably reduces the effectiveness of the distillation, leaving potential performance improvements for the student on the table. Further, the difficulties in fine-tuning small student models after the initial distillation, without degrading their performance, requires us to both pre-train and fine-tune the teachers on the tasks we want the student to be able to perform. Training a student model through knowledge distillation will, therefore, require more training compared to only training the teacher, which limits the benefits of a student model to inference-time.

As you know, we recently announced the new $1M AAAI Squirrel AI Award for AI for the Benefit of Humanity. The award recognizes positive impacts of AI to protect, enhance, and improve human life in meaningful ways with long-lived effects. I am thrilled to share the news that Regina Barzilay of MIT is the inaugural recipient of the award. Regina is recognized for fundamental advances in AI for healthcare, being a proactive community builder and role model, and demonstrating significant impact in people's lives through cancer diagnosis, drug-resistant microbe antibiotics, and drug discovery. The award will be given at the AAAI conference in February, and the associated prize of $1 million will be provided by the online education company Squirrel AI.

The excitement of using Artificial Intelligence has not dwindled from the time it has been unfolded. In KPMG study on “living in the AI world 2020: achievements and challenges of AI across 5 industries (retail, financial service, healthcare, transportation, and technology), revealed that 92% of respondents agreed that leveraging the spectrum of AI technologies will make their companies run more efficiently. Amidst the admiration towards AI, IBM created the Women Leaders in AI program in 2019. This was a way to acknowledge the women leading in AI and encourage females to lend a hand in the field of AI. Through this IBM, planned to make the efforts of the honourees more visible to the world. 2020 IBM women leaders were honoured for outstanding leadership in the AI space. Here is the list of women leaders in AI 2020 honorees:- Aarthi Fernandez Who is a Global head of Trade Operations and SEA Trade COO at Standard Chartered Bank? She is a C-suite executive with deep insight on how digitalization can positively disrupt US$17 trillion global trade. She is into deploying AI/Machine learning to make trade financing simple, faster, and better for corporate clients and mitigate compliance risk. Piera Valeria Cordaro She is a commercial Operations Innovation Manager, Wing Tre S.p.A., Italy. She is a speaker, advocating the use of AI in customer operations. Along with her team and with support by IBM Watson, implemented two chatbots, to improve customer experience. Both bots have made it possible to handle a million queries efficiently. Amala Duggirala Who is the enterprise Chief operation and Technology officer, Regions Bank, United States. To handle customers’ inquiries she deployed IBM Watson’s assistant- virtual banker persona, ”Reggie”. From the time of its implementation 4.3 million customer calls have been answered, with 22% of them being handled by AI. Mara Reiff Vice President, Strategy and Business Intelligence, Beli Canada, Canada. She used AI to improve operations, loyalty, and brand. She worked with IBM to install Watson studio Local using Red Hat open shift. This resulted in smarter, fast decision-making with improved customer experience leading to increased sales. Mara suggests everybody to “Make sure to stop and smell the roses. Take each opportunity to learn something new and embrace change”. Amy Shreve- McDonald She is lead Product Marketing Manager for Business Digital experience, AI&T, USA. EVA (Enterprise Virtual Agent) was launched in February 2019, to improve customer chat experience, it uses Watson assistant. This system has been able to handle 45% chats on its own, resulting in reduced costs and expanding 24/7 support. She also received AT&T’s 2019 Visionary Award for her work advocating EVA. Ryoko Miyashita Manager, customer service department, customer service section JACCS CO., LTD Japan. She launched a Watson-enabled operator onboarding tool, that resulted in reduced new operator training period by 30%. The tool has increase customer satisfaction. Her advice to the younger self is “It is important to believe in yourself, but it is equally or more important to believe in people around you. I would encourage myself to have many experiences and garner knowledge to objectively evaluate things, not blindly accept or exclude others’ opinions”. Carol Chen She is Vice President for Global Marketing, Global Commercial, Royal Dutch Shell, United Kingdom. Along with her team, Carol is partnering is planning for digital transformation with the creation of “Oren”- a Smart Minning Platform, by partnering with IBM. This platform will offer an innovative and creative experience for users in the sector to deliver connectivity and integration across the ecosystem. To use AI, she advice commencing with analyzing the business outcome that one wants and customer pain points that one can cater to. The next step would be to determine how to leverage AI and data to solve the problem. Rosa Martinez Cognitive Project Manager, CiaxaBank, Spain. For those who consider using AI, her advice to them is ‘first to understand the business case as it may take time more than expected. This phase can result in a non-AI project example a ‘software as usual’. But moving further with the project there can be more AI application for sure to work on’. Lee- Lim Sok Know Deputy Principal, Temasek Polytechnic, Singapore. Under the leadership of Sok Keow, The higher education institution in Singapore ‘Temasek Polytechnic’ launched the “Ask TP” chatbot in January 2018. The chatbot helped current as well as prospective students to get answers to the questions asked about Temasek and also gave personalized course advice. In the 1st two weeks of 2020, ‘Ask’ TP’ responded to more than4,351 questions. She suggests everybody “deeply appreciate ‘people’ as they are the most critical asset in an organization, and a leader must develop a team”. Itumeleng Monale Executive Head of Enterprise Information Management Personal and Business Banking, Standard Bank of South Africa, South Africa. By deploying many analytical tools in her organization, she can uplift the revenue of the company. Through models of analytics relationships, bankers are experiencing a 40% revenue uplift when comparing to their peers. She sees AI as a tool through which business delivery can be accelerated, value could be added to human capital and relationships can build further. With this AI era, Research has postulated that corporate giants still have less percentage of women in the technical department. Facebook’s diversity report suggests that there are 22 % of women in the technical department and 15 per cent of women work in the AI research group. Similarly, Google’s diversity report suggests that only 10% women are working on  “machine intelligence”. There is a need to encourage women participation as there are many more women around the world, stepping out of the pre-existed sheathe and going beyond the walls to shape the future. Opening up the AI platform for all will fetch us more talented beings which can help us celebrate the use of AI in different fields and different ways. Reference:- https://www.ibm.com/watson/women-leaders-in-ai/2020-list https://advisory.kpmg.us/content/dam/advisory/en/pdfs/2020/technology-living-in-an-ai-world.pdf   About the author:- Kirti Kumar is a budding HR professional currently pursuing PGDM in HR and Marketing at New Delhi Institue of Management. She looks forward to opportunities that can hone her skills. She is agile in her attitude with versatility in her action

Melanie Mitchell is the Davis Professor of Complexity at the Santa Fe Institute, and Professor of Computer Science at Portland State University. Prof. Mitchell is the author of a number of interesting books such as Complexity: A Guided Tour and Artificial Intelligence: A Guide for Thinking Humans. One interesting detail of her academic bio is that Douglas Hofstadter was her Ph.D. supervisor. During this 90 min interview with Melanie Mitchell, we cover a variety of interesting topics such as: how she started in physics, went into math, and ended up in Computer Science; how Douglas Hofstadter became her Ph.D. supervisor; the biggest issues that humanity is facing today; my predictions of the biggest challenges of the next 100 days of the COVID19 pandemic; how to remain hopeful when it is hard to be optimistic; the problems in defining AI, thinking and human; the Turing Test and Ray Kurzweil's bet with Mitchell Kapor; the Technological Singularity and its possible timeline; the Fallacy of First Steps and the Collapse of AI; Marvin Minsky's denial of progress towards AGI; Hofstadter's fear that intelligence may turn out to be a set of "cheap tricks"; the importance of learning and interacting with the world; the [hard] problem of consciousness; why it is us who need to sort ourselves out and not rely on God or AI; complexity, the future and why living in "Uncertain Times" is an unprecented opportunity. Intelligence is a very complex phenomenon and we should study it as such.

This article is part of "AI education", a series of posts that review and explore educational content on data science and machine learning. How much math knowledge do you need for machine learning and deep learning? Some people say not much. Both are correct, depending on what you want to achieve. There are plenty of programming libraries, code snippets, and pretrained models that can get help you integrate machine learning into your applications without having a deep knowledge of the underlying math functions.

The 2020 Breakthrough Days event aims to generate and fuel meaningful projects in each of this year's three AI for Good Global Summit domains – Gender, Food, and Pandemics – that will advance progress on the UN Sustainable Development Goals (SDGs). Hear from keynote speakers and participate in interactive workshops designed to launch solutions to some of the world's greatest challenges. "Beneficial AI to advance SDGs" Keynote Speaker: Stuart Russell, Professor of Computer Science at UC Berkeley Moderator: Amir Banifatemi, Chief Innovation Officer, XPRIZE; Chair of the AI for Good Programme Committee In an effort to allow teams to prepare for main stage presentations on Monday and Tuesday, we have designated Friday 25 September as a time for teams and attendees to converse individually. Please use the AI for Good workspace on Slack to continue the conversation. Join us on Monday 28 September as we hear from teams in each of this year's AI for Good Breakthrough Track "What is AI for Good Anyway?" Keynote Speaker: Sasha Luccioni, Postdoctoral Researcher – AI for Humanity, Université de Montréal, Mila – Quebec AI Institute Moderator: Amir Banifatemi, Chief Innovation Officer, XPRIZE; Chair of the AI for Good Programme Committee Keynote Address Keynote Speaker: Peter H. Diamandis, entrepreneur, founder and executive chairman of the XPRIZE Foundation, Bestselling author of "Abundance – The Future Is Better Than You Think" Moderator: Amir Banifatemi, Chief Innovation Officer, XPRIZE; Chair of the AI for Good Programme Committee Interested individuals and teams from around the world have submitted project ideas to the Gender, Food and Pandemics Breakthrough Tracks. After being mentored by world-renowned experts and Brain Trusts, the top three finalists in each domain have been selected to present their project proposals in a series of interactive workshops during the Breakthrough Days event.

Elite institutions, the self-appointed arbiters of ethics are guilty of racism and unethical behavior but have zero accountability. In July 2020, MIT took a frequently cited and widely used dataset offline when two researchers found that the '80 Million Tiny Images' dataset used racist, misogynistic terms to describe images of Black and Asian people. According to The Register, Vinay Prabhu, a data scientist of Indian origin working at a startup in California, and Abeba Birhane, an Ethiopian PhD candidate at University College Dublin, who made the discovery that thousands of images in the MIT database were "labeled with racist slurs for Black and Asian people, and derogatory terms used to describe women." This problematic dataset was created back in 2008 and if left unchecked, it would have continued to spawn biased algorithms and introduce prejudice into AI models that used it as training dataset. This incident also highlights a pervasive tendency in this space to put the onus of solving ethical problems created by questionable technologies back on the marginalized groups negatively impacted by them. IBM's recent decision to exit the Facial Recognition industry, followed by similar measures by other tech giants, was in no small part due to the foundational work of Timnit Gebru, Joy Buolamwini, and other Black women scholars.

Artificial intelligence and deep learning are drawing patterns out of the seeming noise in big data, and it's changing our world in broad and subtle ways: Finding practical uses for holograms, developing new tools for first responders, and even writing our creepy campfire stories for us. AI and deep learning are becoming an indispensable skill for IT professionals, academics, and anyone who handles large data sets or needs to use heavy processing power to solve problems. The Deep Learning & Data Analysis Certification Bundle, currently at 97% off, has all the tools you need to begin teaching computers how to dig into datasets, whether you're completely new to the field or looking to sharpen your skills. If you're completely new to AI and deep learning, "Business Data Visualization, Analytics & Reporting with Google Data Studio" lays out how to use Google's free tool for taking large amounts of data and turning it into easy-to-read visualizations, from simple charts and graphs to more complex designs. You'll learn how computers handle these tasks, how to think about data visually and ground yourself in the basics of statistics.