Haggai Maron, Or Litany, Gal Chechik and Ethan Fetaya received an Outstanding Paper Award at ICML2020 for their work On Learning Sets of Symmetric Elements. Here, lead author Haggai tells us more about their research, how he goes about solving problems, and plans for future work in this area. We target learning problems in which the input is a set of images or other structured objects like graphs. The challenge here is building a learning model that does not pay attention to the order of the elements and at the same time respects their structure. For example: imagine you have several photos of a scene on your smartphone, and you want to select a single high-quality photo.

With machine learning models being increasingly applied to various decision-making scenarios, people have spent growing efforts to make machine learning models more transparent and explainable. Among various explanation techniques, counterfactual explanations have the advantages of being human-friendly and actionable -- a counterfactual explanation tells the user how to gain the desired prediction with minimal changes to the input. Besides, counterfactual explanations can also serve as efficient probes to the models' decisions. In this work, we exploit the potential of counterfactual explanations to understand and explore the behavior of machine learning models. We design DECE, an interactive visualization system that helps understand and explore a model's decisions on individual instances and data subsets, supporting users ranging from decision-subjects to model developers. DECE supports exploratory analysis of model decisions by combining the strengths of counterfactual explanations at instance- and subgroup-levels. We also introduce a set of interactions that enable users to customize the generation of counterfactual explanations to find more actionable ones that can suit their needs. Through three use cases and an expert interview, we demonstrate the effectiveness of DECE in supporting decision exploration tasks and instance explanations.

Amy Barrett: So Girl Decoded was published earlier this year by Penguin Business. Can you tell me, what is your book about? Rana el Kaliouby: So my book is a memoir. It's a juxtaposition of my personal journey intertwined with my journey building emotional intelligence into technology. AB: What made you actually want to start writing it? ReK: So the initial idea was to talk about emotion A.I. or artificial emotional intelligence and kind of tease apart the different applications of the technology and the ethical and moral implications of building technology like that. But very early on, I remember meeting with the publisher Penguin, Random House, and the editor there said, you know, your story is really fascinating. I grew up in the Middle East, found my way to the US by way of studying in the UK, actually. Ane he said, that's the story, you got to interweave your personal stories. So it ended up being this, again, kind of inter woven mix of my personal background and how I went from what I call "a nice Egyptian girl" to a CEO of a tech company. AB: And what some of the biggest challenges you say you faced to getting where you are today? ReK: I think the biggest kind of challenge is that I was always kind of doing some… I'm a misfit. Like, I grew up in the Middle East, but I really wanted to be a computer scientist. I left home to do my PhD, which was quite unusual at the time because my husband at the time had to stay back in Cairo for work.

The United States government is one of the largest buyers in the world, if not the largest, spending over $4.1 Trillion annually overall with hundreds of billions spent on technology. As part of all this, the General Services Administration (GSA), a key agency in the US federal government is responsible for managing many of the operations of the federal system including many aspects of procurement. Increasingly the GSA is leveraging AI and machine learning to help optimize, manage, and advance procurement functions. AI and ML are providing key ability to optimize procurement processes, provide visibility into key metrics, and generate insights and forecasts to procurement trends. In this article, Keith Nakasone, Deputy Assistant Commissioner, Acquisition, Office IT Category at the GSA shares insights on how AI is impacting federal government procurement as a follow-up to a recent podcast interview on this topic.

Tedrake, a robotics researcher at MIT, has taken part in the challenge, and describes how hard it is to even get a robot in a car. What do you think about RoboSimian and its smooth yet creepy way of exiting a vehicle? And how do you think "Clyde" compares to Boston Dynamics' Atlas? Let us know your thoughts in the comments!

I recently started a new newsletter focus on AI education. TheSequence is a no-BS( meaning no hype, no news etc) AI-focused newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. Memory modeling is an active area of research in the deep learning space. In recent years, techniques such as Neural Turing Machines(NTM) have made significant progress setting up the foundation for building human-like memory structures in deep learning systems.

So what are we gonna talk about this time? Last time, we saw many examples of how the work in AI had been going on from centuries, like Aristotle in 300 BC or George Boole in the 19th century. But, if you were to go back in time to that part of the history, you would see that there wasn't any field called Artificial Intelligence. Only in the summer of 1956 at Dartmouth College, Hanover(USA), did some sort of formalization start happening. This incident stoked the fire which ultimately decided the course of a field very disorganized at that point in time.

In mid-2019, I shared 9 Ways That Artificial Intelligence Might Disrupt Authors and Publishing, and one of those possible disruptions concerned voice technologies, which I also wrote about in Audio for Authors. In 2020, we have seen an acceleration of AI with the release of GPT-3 for natural language processing and generation, as well as the development of ever more sophisticated voice recognition and creation. In this episode, Mark Leslie Lefebvre and I share a conversation between our Voice Doubles and our thoughts on the ramifications. You can get your own Voice Double at Descript.com. You can find Mark at MarkLeslie.ca. Mark also recorded a special episode with more of his thoughts in episode 148 of Stark Reflections. We'd love to know what you think so please leave a comment or tweet me @thecreativepenn and Mark @markleslie So, how's lockdown where you are? How are things in Canada? Mark: Lockdown has actually allowed me to discover new types of creativity in myself, where I seem to have prevented myself from writing prose. So I have the energy inside me to tell story, to want to share and amuse and entertain, and I redirected it into a different output that satisfied that part of my soul that needs to write, and now I'm back writing again. But while I was struggling, it was really good to have that outlet. Jo: I also struggled at the beginning, and I did a flurry of business activities.

Technovation, a global technology education nonprofit, announced that two teams of girls and two family teams - representing Kazakhstan, Kuwait, India and Ireland - were named winners at its annual Technovation World Summit held virtually August 13-14. The two-day event brought together more than 1,000 members and supporters of the Technovation community from around the world. The Awards Ceremony, held during World Summit, is a culmination of the annual Technovation Girls and Technovation Families programs in which nearly 2,000 teams of girls (ages 10-18) and families (with children ages 8-16) are challenged to develop a mobile application or AI prototype to solve an issue they've identified in their community. This year, teams across 60 countries overcame incredible odds stemming from COVID-19 to participate with the support of more than 3,500 mentors and chapter ambassadors. All finalists will receive a portion of the nearly $30,000 being awarded.

In 2014, the DBSCAN algorithm was awarded the test of time award (an award given to algorithms which have received substantial attention in theory and practice) at the leading data mining conference, ACM SIGKDD. Clustering analysis is an unsupervised learning method that separates the data points into several specific bunches or groups, such that the data points in the same groups have similar properties and data points in different groups have different properties in some sense. It comprises of many different methods based on different distance measures. Centrally, all clustering methods use the same approach i.e. first we calculate similarities and then we use it to cluster the data points into groups or batches. Here we will focus on the Density-based spatial clustering of applications with noise (DBSCAN) clustering method. If you are unfamiliar with the clustering algorithms, I advise you to read the Introduction to Image Segmentation with K-Means clustering.