Hiring partners tell us all the time that they want candidates who are excited about the field of autonomous vehicles. That's part of what makes the Udacity Self-Driving Car Engineer Nanodegree Program so impressive -- students from around the world have sought out the program in order to learn about the field. In addition to the twelve different projects students must pass to earn the Nanodegree credential, many of our students go even further and build independent projects of their own. Here are a few projects that different students have undertaken. Maybe they can inspire you to build your own independent project!

Are our machines turning into gods? Jie, the world's best player of the world's oldest board game, Go, had just met his match… in the form of a program called AlphaGo. In the space of a year, the program had become "almost like the god of Go," said Jie after losing to AlphaGo. Jie had been playing the game, viewed as too hard for machines to excel at, since he was 10. AlphaGo was only made by Google's parent, Alphabet, in 2014.

Conventionally, the questions on a test are assumed to be kept secret from test takers until the test. However, for tests that are taken on a large scale, particularly asynchronously, this is very hard to achieve. For example, TOEFL iBT and driver's license test questions are easily found online. This also appears likely to become an issue for Massive Open Online Courses (MOOCs, as offered for example by Coursera, Udacity, and edX). Specifically, the test result may not reflect the true ability of a test taker if questions are leaked beforehand. In this paper, we take the loss of confidentiality as a fact. Even so, not all hope is lost as the test taker can memorize only a limited set of questions' answers, and the tester can randomize which questions to let appear on the test. We model this as a Stackelberg game, where the tester commits to a mixed strategy and the follower responds. Informally, the goal of the tester is to best reveal the true ability of a test taker, while the test taker tries to maximize the test result (pass probability or score). We provide an exponential-size linear program formulation that computes the optimal test strategy, prove several NP-hardness results on computing optimal test strategies in general, and give efficient algorithms for special cases (scored tests and single-question tests). Experiments are also provided for those proposed algorithms to show their scalability and the increase of the tester's utility relative to that of the uniform-at-random strategy. The increase is quite significant when questions have some correlation---for example, when a test taker who can solve a harder question can always solve easier questions.

Simultaneously recorded electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) can be used to non-invasively measure the spatiotemporal dynamics of the human brain. One challenge is dealing with the artifacts that each modality introduces into the other when the two are recorded concurrently, for example the ballistocardiogram (BCG). We conducted a preliminary comparison of three different MR compatible EEG recording systems and assessed their performance in terms of single-trial classification of the EEG when simultaneously collecting fMRI. We found tradeoffs across all three systems, for example varied ease of setup and improved classification accuracy with reference electrodes (REF) but not for pulse artifact subtraction (PAS) or reference layer adaptive filtering (RLAF).

Electricity theft is a major problem around the world in both developed and developing countries and may range up to 40% of the total electricity distributed. More generally, electricity theft belongs to non-technical losses (NTL), which are losses that occur during the distribution of electricity in power grids. In this paper, we build features from the neighborhood of customers. We first split the area in which the customers are located into grids of different sizes. For each grid cell we then compute the proportion of inspected customers and the proportion of NTL found among the inspected customers. We then analyze the distributions of features generated and show why they are useful to predict NTL. In addition, we compute features from the consumption time series of customers. We also use master data features of customers, such as their customer class and voltage of their connection. We compute these features for a Big Data base of 31M meter readings, 700K customers and 400K inspection results. We then use these features to train four machine learning algorithms that are particularly suitable for Big Data sets because of their parallelizable structure: logistic regression, k-nearest neighbors, linear support vector machine and random forest. Using the neighborhood features instead of only analyzing the time series has resulted in appreciable results for Big Data sets for varying NTL proportions of 1%-90%. This work can therefore be deployed to a wide range of different regions around the world.

The paper deals with regression problems, in which the nonsmooth target is assumed to switch between different operating modes. Specifically, piecewise smooth (PWS) regression considers target functions switching deterministically via a partition of the input space, while switching regression considers arbitrary switching laws. The paper derives generalization error bounds in these two settings by following the approach based on Rademacher complexities. For PWS regression, our derivation involves a chaining argument and a decomposition of the covering numbers of PWS classes in terms of the ones of their component functions and the capacity of the classifier partitioning the input space. This yields error bounds with a radical dependency on the number of modes. For switching regression, the decomposition can be performed directly at the level of the Rademacher complexities, which yields bounds with a linear dependency on the number of modes. By using once more chaining and a decomposition at the level of covering numbers, we show how to recover a radical dependency, however at the cost of a slightly worse convergence rate. Examples of applications are given in particular for PWS and swichting regression with linear and kernel-based component functions.

In this study, the wind data series from five locations in Aegean Sea islands, the most active `hotspots' in terms of refugee influx during the Oct/2015 - Jan/2016 period, are investigated. The analysis of the three-per-site data series includes standard statistical analysis and parametric distributions, auto-correlation analysis, cross-correlation analysis between the sites, as well as various ARMA models for estimating the feasibility and accuracy of such spatio-temporal linear regressors for predictive analytics. Strong correlations are detected across specific sites and appropriately trained ARMA(7,5) models achieve 1-day look-ahead error (RMSE) of less than 1.9 km/h on average wind speed. The results show that such data-driven statistical approaches are extremely useful in identifying unexpected and sometimes counter-intuitive associations between the available spatial data nodes, which is very important when designing corresponding models for short-term forecasting of sea condition, especially average wave height and direction, which is in fact what defines the associated weather risk of crossing these passages in refugee influx patterns.

Inference and Estimation in Missing Information (MI) scenarios are important topics in Statistical Learning Theory and Machine Learning (ML). In ML literature, attempts have been made to enhance prediction through precise feature selection methods. In sparse linear models, LASSO is well-known in extracting the desired support of the signal and resisting against noisy systems. When sparse models are also suffering from MI, the sparse recovery and inference of the missing models are taken into account simultaneously. In this paper, we will introduce an approach which enjoys sparse regression and covariance matrix estimation to improve matrix completion accuracy, and as a result enhancing feature selection preciseness which leads to reduction in prediction Mean Squared Error (MSE). We will compare the effect of employing covariance matrix in enhancing estimation accuracy to the case it is not used in feature selection. Simulations show the improvement in the performance as compared to the case where the covariance matrix estimation is not used.

This work falls within the context of predicting the value of a real function at some input locations given a limited number of observations of this function. The Kriging interpolation technique (or Gaussian process regression) is often considered to tackle such a problem but the method suffers from its computational burden when the number of observation points is large. We introduce in this article nested Kriging predictors which are constructed by aggregating sub-models based on subsets of observation points. This approach is proven to have better theoretical properties than other aggregation methods that can be found in the literature. Contrarily to some other methods it can be shown that the proposed aggregation method is consistent. Finally, the practical interest of the proposed method is illustrated on simulated datasets and on an industrial test case with $10^4$ observations in a 6-dimensional space.

We propose kernel sequential Monte Carlo (KSMC), a framework for sampling from static target densities. KSMC is a family of sequential Monte Carlo algorithms that are based on building emulator models of the current particle system in a reproducing kernel Hilbert space. We here focus on modelling nonlinear covariance structure and gradients of the target. The emulator's geometry is adaptively updated and subsequently used to inform local proposals. Unlike in adaptive Markov chain Monte Carlo, continuous adaptation does not compromise convergence of the sampler. KSMC combines the strengths of sequental Monte Carlo and kernel methods: superior performance for multimodal targets and the ability to estimate model evidence as compared to Markov chain Monte Carlo, and the emulator's ability to represent targets that exhibit high degrees of nonlinearity. As KSMC does not require access to target gradients, it is particularly applicable on targets whose gradients are unknown or prohibitively expensive. We describe necessary tuning details and demonstrate the benefits of the the proposed methodology on a series of challenging synthetic and real-world examples.