Diagnosing cancer is about to get more accurate, with the help of artificial intelligence. Pathologists have diagnosed diseases in more or less the same way for the past 100 years, by laboring over a microscope reviewing biopsy samples on little glass slides. Working almost robotically, they sift through millions of normal cells to identify just a few diseased ones. The task is tedious and prone to human error. But now, scientists and engineers have created a technique that uses artificial intelligence (AI) and can differentiate cancer cells from normal cells almost as well as a top-notch pathologist.

Broadly speaking, educational activities can be split into two categories: life skills and professional skills. The life skills that we all need to learn, and the way we learn them, have remained relatively consistent across the ages: how to communicate, socialize and survive. But you can argue that today's education system is skewed toward the second category, the teaching of professional skills and it's this category that will face the greatest opportunities and challenges over the next 50 years. While educators prepare students for lives of learning, it's more true to say their role is to prepare students for lifelong careers. But while that was a relatively simple task in the past, it's now much more difficult.

Conventional collaborative filtering techniques treat a top-n recommendations problem as a task of generating a list of the most relevant items. This formulation, however, disregards an opposite - avoiding recommendations with completely irrelevant items. Due to that bias, standard algorithms, as well as commonly used evaluation metrics, become insensitive to negative feedback. In order to resolve this problem we propose to treat user feedback as a categorical variable and model it with users and items in a ternary way. We employ a third-order tensor factorization technique and implement a higher order folding-in method to support online recommendations. The method is equally sensitive to entire spectrum of user ratings and is able to accurately predict relevant items even from a negative only feedback. Our method may partially eliminate the need for complicated rating elicitation process as it provides means for personalized recommendations from the very beginning of an interaction with a recommender system. We also propose a modification of standard metrics which helps to reveal unwanted biases and account for sensitivity to a negative feedback. Our model achieves state-of-the-art quality in standard recommendation tasks while significantly outperforming other methods in the cold-start "no-positive-feedback" scenarios.

Online surveys have the potential to support adaptive questions, where later questions depend on earlier responses. Past work has taken a rule-based approach, uniformly across all respondents. We envision a richer interpretation of adaptive questions, which we call dynamic question ordering (DQO), where question order is personalized. Such an approach could increase engagement, and therefore response rate, as well as imputation quality. We present a DQO framework to improve survey completion and imputation. In the general survey-taking setting, we want to maximize survey completion, and so we focus on ordering questions to engage the respondent and collect hopefully all information, or at least the information that most characterizes the respondent, for accurate imputations. In another scenario, our goal is to provide a personalized prediction. Since it is possible to give reasonable predictions with only a subset of questions, we are not concerned with motivating users to answer all questions. Instead, we want to order questions to get information that reduces prediction uncertainty, while not being too burdensome. We illustrate this framework with an example of providing energy estimates to prospective tenants. We also discuss DQO for national surveys and consider connections between our statistics-based question-ordering approach and cognitive survey methodology.

Causal modeling has long been an attractive topic for many researchers and in recent decades there has seen a surge in theoretical development and discovery algorithms. Generally discovery algorithms can be divided into two approaches: constraint-based and score-based. The constraint-based approach is able to detect common causes of the observed variables but the use of independence tests makes it less reliable. The score-based approach produces a result that is easier to interpret as it also measures the reliability of the inferred causal relationships, but it is unable to detect common confounders of the observed variables. A drawback of both score-based and constrained-based approaches is the inherent instability in structure estimation. With finite samples small changes in the data can lead to completely different optimal structures. The present work introduces a new hypothesis-free score-based causal discovery algorithm, called stable specification search, that is robust for finite samples based on recent advances in stability selection using subsampling and selection algorithms. Structure search is performed over Structural Equation Models. Our approach uses exploratory search but allows incorporation of prior background knowledge. We validated our approach on one simulated data set, which we compare to the known ground truth, and two real-world data sets for Chronic Fatigue Syndrome and Attention Deficit Hyperactivity Disorder, which we compare to earlier medical studies. The results on the simulated data set show significant improvement over alternative approaches and the results on the real-word data sets show consistency with the hypothesis driven models constructed by medical experts.

OBJECTIVE: We aim to extract and denoise the attended speaker in a noisy, two-speaker acoustic scenario, relying on microphone array recordings from a binaural hearing aid, which are complemented with electroencephalography (EEG) recordings to infer the speaker of interest. METHODS: In this study, we propose a modular processing flow that first extracts the two speech envelopes from the microphone recordings, then selects the attended speech envelope based on the EEG, and finally uses this envelope to inform a multi-channel speech separation and denoising algorithm. RESULTS: Strong suppression of interfering (unattended) speech and background noise is achieved, while the attended speech is preserved. Furthermore, EEG-based auditory attention detection (AAD) is shown to be robust to the use of noisy speech signals. CONCLUSIONS: Our results show that AAD-based speaker extraction from microphone array recordings is feasible and robust, even in noisy acoustic environments, and without access to the clean speech signals to perform EEG-based AAD. SIGNIFICANCE: Current research on AAD always assumes the availability of the clean speech signals, which limits the applicability in real settings. We have extended this research to detect the attended speaker even when only microphone recordings with noisy speech mixtures are available. This is an enabling ingredient for new brain-computer interfaces and effective filtering schemes in neuro-steered hearing prostheses. Here, we provide a first proof of concept for EEG-informed attended speaker extraction and denoising.

With the increase in adoption of Electric Vehicles (EVs), proper utilization of the charging infrastructure is an emerging challenge for service providers. Overstaying of an EV after a charging event is a key contributor to low utilization. Since overstaying is easily detectable by monitoring the power drawn from the charger, managing this problem primarily involves designing an appropriate "penalty" during the overstaying period. Higher penalties do discourage overstaying; however, due to uncertainty in parking duration, less people would find such penalties acceptable, leading to decreased utilization (and revenue). To analyze this central trade-off, we develop a novel framework that integrates models for realistic user behavior into queueing dynamics to locate the optimal penalty from the points of view of utilization and revenue, for different values of the external charging demand. Next, when the model parameters are unknown, we show how an online learning algorithm, such as UCB, can be adapted to learn the optimal penalty. Our experimental validation, based on charging data from London, shows that an appropriate penalty can increase both utilization and revenue while significantly reducing overstaying.

Event[0] is a game about a stranded astronaut talking to an artificial intelligence to help them get back to earth. Like Firewatch before it, much of this solitary adventure is centered around conversing with your colleague. Unlike Firewatch, your colleague is a computer recalling 2001's HAL. Also unlike Firewatch, you get to manually type in the questions you'd like to ask. There's no prescribed dialogue trees here, folks.

At the International Symposium on Biomedical Imaging in Prague, a Harvard-based artificial intelligence system won the Camelyon16 challenge, a competition comprised of participants introducing their individual AI systems and its ability to facilitate automated lymph node metastasis diagnosis. Referred to as PathAl, the computing system identifies cancerous cells through a mechanism referred to as deep learning--an algorithmic technique that accumulates copious amounts of unstructured data and organizes it into clusters, before analyzing it for patterns. Deep learning is predominately utilized in speech recognition systems like Apple's Siri and Microsoft's Cortana. According to one of the challenge's organizers, Jeroen van der Laak of Radboud University Medical Center in Netherlands, the technology featured in the competition went "way beyond" his expectations, as the AI's accuracy proved strikingly close to that of human beings. In addition, van der Laak said AI technology has the propensity to intrinsically redefine the way histopathological images are handled in the medical community.

Everyone who gets going in Machine Learning (and Deep Learning) gets overwhelmed by the plethora of MOOCs available. Here, I try to give a comprehensive survey of such courses available freely on the internet. You can take this post as an complementary to this and this previous posts. I will try to highlight some important pointers such as the difficulty of the courses, the correct order in which these should to be completed, the right audience for these courses. You will get a feel of how these courses give you a stack of skills in your arsenal and how you can use them to develop practical machine learning systems.