Collaborating Authors


The Open Loop of ML


Over the last few years, I have watched hundreds of students and engineers building machine learning models. I have had many opportunities to be part of the jury in project competitions of Engineering Colleges. Similarly, I have served as a judge in a number of hackathons where I saw the contestants building models and systems in 36 or 48 hours, working day and night. As part of my responsibilities, I have reviewed the work of many interns and also interviewed several candidates for ML engineering positions. They all aim to solve challenging and groundbreaking problems.

Chatbots Revolutionizing the Concept of Online Education


The rapid advancement of technology has drastically changed our lives in a significant amount of ways. It has been observed that almost half of the population has completely relied on modern technologies to get their daily routine tasks completed easily and efficiently. For Instance, from ordering the food online to paying their bills using online wallet apps and taking online classes, all are encompassed in the various forms of the latest technologies. In the past few years, we have witnessed an immense shift from the conventional ways of education into the latest education methods. This pandemic led to the physical closure of educational institutes, schools, colleges, universities, and the overall educational process has shifted towards the online mode of education.

'A train wreck': what happens to workers and towns when the lights go out on coal power?

The Guardian > Energy

When Jacqui Coleman heard that Australia's largest coal-fired power station was to close seven years earlier than planned, she initially didn't believe it. Coleman is a retail worker in Dora Creek, the closest suburb to the Eraring power station on the shores of Lake Macquarie in New South Wales. For years, she has been selling pies, coffees and sandwiches to some of the hundreds of workers who pass through the News'n' More grocery store on either side of a shift. On Thursday morning, Origin Energy announced it was bringing forward the station's closure to 2025. Many workers at the site first learned their jobs were to be terminated seven years early when they heard it reported on the radio.

A General Framework for Modelling Conditional Reasoning -- Preliminary Report Artificial Intelligence

Conditionals are generally considered the backbone of human (and AI) reasoning: the "if-then" connection between two propositions is the stepping stone of arguments and a lot of the research effort in formal logic has focused on this kind of connection. A conditional connection satisfies different properties according to the kind of arguments it is used for. The classical material implication is appropriate for modelling the "ifthen" connection as it is used in Mathematics, but the equivalence between the material implication A B and A B is not appropriate for many other contexts.

Artificial Intelligence and Education: Protecting the Heritage of Humanity


The COVID-19 pandemic has transformed our lives in more ways than one. It has not just alerted us to the vulnerabilities of our health systems but also how ill-equipped our education systems are to cope with disruptions of this scale. When the pandemic forced schools to shut down and learners had to completely switch to online learning systems, the transition was anything but smooth. As part of the coordinated global education response to the COVID-19 pandemic, UNESCO, UNICEF and the World Bank conducted a Survey on National Education Responses to COVID-19 school closures. According to this joint report, 108 countries reported missing an average of 47 days of in-person instruction due to school closures - the equivalent to approximately one quarter of a regular school year – a long gap in the life of a student.

Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Belief Artificial Intelligence

In the absence of prescribed coordination, it is often necessary for individual agents to synthesize their own plans, taking into account not only their own capabilities and beliefs about the world but also their beliefs about other agents, including what each of the agents will come to believe as the consequence of the actions of others. To illustrate, consider the scenario where Larry and Moe meet on a regular basis at the local diner to swap the latest gossip. Larry has come to know that Nancy (Larry's daughter) has just received a major promotion in her job, but unbeknownst to him, Moe has already learned this bit of information through the grapevine. Before they speak, both believe Nancy is getting a promotion, Larry believes Moe is unaware of this (and consequently wishes to share the news), and Moe assumes Larry must already be aware of the promotion but is unaware of Moe's own knowledge of the situation. Very quickly we can see how the nesting of (potentially incorrect) belief can be a complicated and interesting setting to model. In this paper, we examine the problem of synthesizing plans in such settings. In particular, given a finite set of agents, each with: (1) (possibly incomplete and incorrect) beliefs about the world and about the beliefs of other agents; and (2) differing capabilities including the ability to perform actions whose outcomes are unknown to other agents; we are interested in synthesizing a plan to achieve a goal condition. Planning is at the belief level and as such, while we consider the execution of actions that can change the state of the world (ontic actions) as well as an agent's state of knowledge or belief (epistemic or more accurately doxastic actions, including communication actions), all outcomes are with respect to belief.

Optimal Prediction of Unmeasured Output from Measurable Outputs In LTI Systems Machine Learning

In this short article, we showcase the derivation of an optimal predictor, when one part of system's output is not measured but is able to be predicted from the rest of the system's output which is measured. According to author's knowledge, similar derivations have been done before but not in state-space representation.

Situated Conditional Reasoning Artificial Intelligence

Conditionals are useful for modelling, but are not always sufficiently expressive for capturing information accurately. In this paper we make the case for a form of conditional that is situation-based. These conditionals are more expressive than classical conditionals, are general enough to be used in several application domains, and are able to distinguish, for example, between expectations and counterfactuals. Formally, they are shown to generalise the conditional setting in the style of Kraus, Lehmann, and Magidor. We show that situation-based conditionals can be described in terms of a set of rationality postulates. We then propose an intuitive semantics for these conditionals, and present a representation result which shows that our semantic construction corresponds exactly to the description in terms of postulates. With the semantics in place, we proceed to define a form of entailment for situated conditional knowledge bases, which we refer to as minimal closure. It is reminiscent of and, indeed, inspired by, the version of entailment for propositional conditional knowledge bases known as rational closure. Finally, we proceed to show that it is possible to reduce the computation of minimal closure to a series of propositional entailment and satisfiability checks. While this is also the case for rational closure, it is somewhat surprising that the result carries over to minimal closure.

A Rational Entailment for Expressive Description Logics via Description Logic Programs Artificial Intelligence

Lehmann and Magidor's rational closure is acknowledged as a landmark in the field of non-monotonic logics and it has also been re-formulated in the context of Description Logics (DLs). We show here how to model a rational form of entailment for expressive DLs, such as SROIQ, providing a novel reasoning procedure that compiles a non-monotone DL knowledge base into a description logic program (dl-program).

The Smoothed Satisfaction of Voting Axioms Artificial Intelligence

We initiate the work towards a comprehensive picture of the smoothed satisfaction of voting axioms, to provide a finer and more realistic foundation for comparing voting rules. We adopt the smoothed social choice framework, where an adversary chooses arbitrarily correlated "ground truth" preferences for the agents, on top of which random noises are added. We focus on characterizing the smoothed satisfaction of two well-studied voting axioms: Condorcet criterion and participation. We prove that for any fixed number of alternatives, when the number of voters $n$ is sufficiently large, the smoothed satisfaction of the Condorcet criterion under a wide range of voting rules is $1$, $1-\exp(-\Theta(n))$, $\Theta(n^{-0.5})$, $ \exp(-\Theta(n))$, or being $\Theta(1)$ and $1-\Theta(1)$ at the same time; and the smoothed satisfaction of participation is $1-\Theta(n^{-0.5})$. Our results address open questions by Berg and Lepelley in 1994 for these rules, and also confirm the following high-level message: the Condorcet criterion is a bigger concern than participation under realistic models.