In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks. For this, we propose a modified knowledge distillation procedure that achieves state-of-the-art uncertainty estimates both for in and out-of-distribution samples. Our contributions include a) demonstrating and adapting to distillation's regularization effect b) proposing a novel target teacher distribution c) a simple augmentation procedure to improve out-of-distribution uncertainty estimates d) shedding light on the distillation procedure through comprehensive set of experiments.

Handwriting disorder (termed dysgraphia) is a far from a singular problem as nearly 8.6% of the population in France is considered dysgraphic. Moreover, research highlights the fundamental importance to detect and remediate these handwriting difficulties as soon as possible as they may affect a child's entire life, undermining performance and self-confidence in a wide variety of school activities. At the moment, the detection of handwriting difficulties is performed through a standard test called BHK. This detection, performed by therapists, is laborious because of its high cost and subjectivity. We present a digital approach to identify and characterize handwriting difficulties via a Recurrent Neural Network model (RNN). The child under investigation is asked to write on a graphics tablet all the letters of the alphabet as well as the ten digits. Once complete, the RNN delivers a diagnosis in a few milliseconds and demonstrates remarkable efficiency as it correctly identifies more than 90% of children diagnosed as dysgraphic using the BHK test. The main advantage of our tablet-based system is that it captures the dynamic features of writing -- something a human expert, such as a teacher, is unable to do. We show that incorporating the dynamic information available by the use of tablet is highly beneficial to our digital test to discriminate between typically-developing and dysgraphic children.

While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided by continual learning, where the non-stationarity is imposed by a sequence of distinct tasks. Most methods in this space assume, however, the knowledge of task boundaries, and focus on alleviating catastrophic forgetting. In this work, we depart from this view and move the focus towards faster remembering - i.e measuring how quickly the network recovers performance rather than measuring the network's performance without any adaptation. We argue that in many settings this can be more effective and that it opens the door to combining meta-learning and continual learning techniques, leveraging their complementary advantages. We propose a framework specific for the scenario where no information about task boundaries or task identity is given. It relies on a separation of concerns into what task is being solved and how the task should be solved. This framework is implemented by differentiating task specific parameters from task agnostic parameters, where the latter are optimized in a continual meta learning fashion, without access to multiple tasks at the same time. We showcase this framework in a supervised learning scenario and discuss the implications of the proposed formalism.

Machine Learning (ML) is a popular buzzword in the field of technology and recently it has entered the eLearning space as well. Machine learning enables computers or machines to make decisions that are data-driven, eliminating the need for explicit programming to execute a task. Machine learning makes use of algorithms that are designed to improve over time depending on the new data they'll be tracking. What if I tell that you've already experienced the benefits of ML without realizing that it's machine learning at work? For instance, if you have tried online food delivery platforms such as UberEATS, have you wondered how the app is able to predict an estimated time of delivery or display a list of popular restaurants near you?

Great Learning, India's leading Ed-tech platform for working professionals today announced that it is expanding its geographic footprint globally to Europe, Asia Pacific, Africa and the Middle East. The company will offer three of its most popular programs in Data Science & Business Analytics (PGP-DSBA - a special international variant of its business analytics program PGP-BABI ranked #1 in India for the last 4 years), Artificial Intelligence & Machine Learning (PGP-AIML) and Cyber Security (SACSP - Stanford Advanced Computer Security Program) in these geographies. Offered in association with two of the top universities of the world, Stanford University and The University of Texas, Austin, these online programs have already attracted learners from 17 countries including the UK, Singapore, South Africa, UAE, etc. These programs, designed and developed by the top-notch faculty of UT Austin and Stanford, are delivered online by Great Learning, utilizing its unique mentored-learning model where personalized mentorship is provided by expert instructors from Great Learning's 750 Global Guru network. The mentors include industry veterans from companies like Google, Microsoft, Amazon and Walmart.

While there is a lot of discussion around the adoption of artificial intelligence (AI), machine learning, and robotic process automation (RPA), too often such conversations overlook the subject of scale and the reality that most of these trends are not technically ready for scaled out operations. Moty Fania, principle engineer for big data analytics at Intel IT, spent some time at the recent Strata conference highlighting this and stressed the importance of process as fundamental to the success of any AI project. He observed, "Developing an excellent AI model(s) that solves a business problem is essential but not sufficient. Successful AI implementation requires deep integration into business processes and the ability to continuously and rapidly deploy AI models to the production environment of a biz domain." After I heard Moty speak, I thought I'd try an experiment.

Artificial intelligence is putting new teeth on the old saw that cheaters never prosper. New companies and new research are applying the cutting edge technology in at least three different ways to combat cheating -- on homework, on the job hunt and even on one's diet. In California, a new company called Crosschq is using machine learning and data analytics to help employers with the job reference process. The technology is meant to help companies avoid bad hires and compare how job candidates present themselves with how their references see them. In Pennsylvania, Drexel University researchers are developing an app that can predict when dieters are likely to lapse on their eating regimen, based on the time of day, the user's emotions -- even the temperature of their skin and heart rate.

How an agent can act optimally in stochastic, partially observable domains is a challenge problem, the standard approach to address this issue is to learn the domain model firstly and then based on the learned model to find the (near) optimal policy. However, offline learning the model often needs to store the entire training data and cannot utilize the data generated in the planning phase. Furthermore, current research usually assumes the learned model is accurate or presupposes knowledge of the nature of the unobservable part of the world. In this paper, for systems with discrete settings, with the benefits of Predictive State Representations~(PSRs), a model-based planning approach is proposed where the learning and planning phases can both be executed online and no prior knowledge of the underlying system is required. Experimental results show compared to the state-of-the-art approaches, our algorithm achieved a high level of performance with no prior knowledge provided, along with theoretical advantages of PSRs. Source code is available at https://github.com/DMU-XMU/PSR-MCTS-Online.

This paper defines the notion of class discrepancy for families of functions. It shows that low discrepancy classes admit small offline and streaming coresets. We provide general techniques for bounding the class discrepancy of machine learning problems. As corollaries of the general technique we bound the discrepancy (and therefore coreset complexity) of logistic regression, sigmoid activation loss, matrix covariance, kernel density and any analytic function of the dot product or the squared distance. Our results prove the existence of epsilon-approximation O(sqrt{d}/epsilon) sized coresets for the above problems. This resolves the long-standing open problem regarding the coreset complexity of Gaussian kernel density estimation. We provide two more related but independent results. First, an exponential improvement of the widely used merge-and-reduce trick which gives improved streaming sketches for any low discrepancy problem. Second, an extremely simple deterministic algorithm for finding low discrepancy sequences (and therefore coresets) for any positive semi-definite kernel. This paper establishes some explicit connections between class discrepancy, coreset complexity, learnability, and streaming algorithms.

Least-mean squares (LMS) solvers such as Linear / Ridge / Lasso-Regression, SVD and Elastic-Net not only solve fundamental machine learning problems, but are also the building blocks in a variety of other methods, such as decision trees and matrix factorizations. We suggest an algorithm that gets a finite set of $n$ $d$-dimensional real vectors and returns a weighted subset of $d+1$ vectors whose sum is \emph{exactly} the same. The proof in Caratheodory's Theorem (1907) computes such a subset in $O(n^2d^2)$ time and thus not used in practice. Our algorithm computes this subset in $O(nd)$ time, using $O(\log n)$ calls to Caratheodory's construction on small but "smart" subsets. This is based on a novel paradigm of fusion between different data summarization techniques, known as sketches and coresets. As an example application, we show how it can be used to boost the performance of existing LMS solvers, such as those in scikit-learn library, up to x100. Generalization for streaming and distributed (big) data is trivial. Extensive experimental results and complete open source code are also provided.