It seems like we've perennially been on the edge of major breakthroughs in AI (artificial intelligence), virtual reality, personal robots, and other such cool tech for the past two decades. The first set of science fiction imaginings came true rather rapidly -- think trans-continental air travel, space stations, even drone warfare -- but it appears that the emergence of next-gen tech wizardry has stalled. But while we still can't chat with the on-board computer on our personal spaceship, artificial intelligence is far more pervasive in our daily lives today than most of us realize. As anyone who has trained their mobile phone assistant can attest, years of painstaking research and investment in artificial intelligence technologies is starting to yield impressive results. Siri can predict our commute patterns, Microsoft Cortana warns us of bad weather, and the Google Assistant diligently sets calendar reminders with the impassive demeanor of an English butler of yore.

Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks (MemN2N) have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namely multi-fact questionanswering, positional reasoning or dialog related tasks, remain challenging particularly due to the necessity of more complex interactions between the memory and controller modules composing this family of models. In this paper, we introduce a novel end-to-end memory access regulation mechanism inspired by the current progress on the connection short-cutting principle in the field of computer vision. Concretely, we develop a Gated End-to- End trainable Memory Network architecture (GMemN2N). From the machine learning perspective, this new capability is learned in an end-to-end fashion without the use of any additional supervision signal which is, as far as our knowledge goes, the first of its kind. Our experiments show significant improvements on the most challenging tasks in the 20 bAbI dataset, without the use of any domain knowledge. Then, we show improvements on the Dialog bAbI tasks including the real human-bot conversion-based Dialog State Tracking Challenge (DSTC-2) dataset. On these two datasets, our model sets the new state of the art.

Cancer survival prediction is an active area of research that can help prevent unnecessary therapies and improve patient's quality of life. Gene expression profiling is being widely used in cancer studies to discover informative biomarkers that aid predict different clinical endpoint prediction. We use multiple modalities of data derived from RNA deep-sequencing (RNA-seq) to predict survival of cancer patients. Despite the wealth of information available in expression profiles of cancer tumors, fulfilling the aforementioned objective remains a big challenge, for the most part, due to the paucity of data samples compared to the high dimension of the expression profiles. As such, analysis of transcriptomic data modalities calls for state-of-the-art big-data analytics techniques that can maximally use all the available data to discover the relevant information hidden within a significant amount of noise. In this paper, we propose a pipeline that predicts cancer patients' survival by exploiting the structure of the input (manifold learning) and by leveraging the unlabeled samples using Laplacian support vector machines, a graph-based semi supervised learning (GSSL) paradigm. We show that under certain circumstances, no single modality per se will result in the best accuracy and by fusing different models together via a stacked generalization strategy, we may boost the accuracy synergistically. We apply our approach to two cancer datasets and present promising results. We maintain that a similar pipeline can be used for predictive tasks where labeled samples are expensive to acquire.

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks, state of the art models in speech recognition and translation. Our approach to increasing interpretability is by combining a long short-term memory (LSTM) model with a hidden Markov model (HMM), a simpler and more transparent model. We add the HMM state probabilities to the output layer of the LSTM, and then train the HMM and LSTM either sequentially or jointly. The LSTM can make use of the information from the HMM, and fill in the gaps when the HMM is not performing well. A small hybrid model usually performs better than a standalone LSTM of the same size, especially on smaller data sets. We test the algorithms on text data and medical time series data, and find that the LSTM and HMM learn complementary information about the features in the text.

At the core of interpretable machine learning is the question of whether humans are able to make accurate predictions about a model's behavior. Assumed in this question are three properties of the interpretable output: coverage, precision, and effort. Coverage refers to how often humans think they can predict the model's behavior, precision to how accurate humans are in those predictions, and effort is either the upfront effort required in interpreting the model, or the effort required to make predictions about a model's behavior. One approach to interpretable machine learning is designing inherently interpretable models. Visualizations of these models usually have perfect coverage, but there is a tradeoff between the accuracy of the model and the effort required to comprehend it - especially in complex domains like text and images, where the input space is very large, and accuracy is usually sacrificed for models that are compact enough to be comprehensible by humans. Experiments usually involve showing humans these visualizations, and measuring human precision when predicting the model's behavior on random instances, and the time (effort) required to make those predictions [7, 8, 9]. Model-agnostic explanations [12] avoid the need to trade off accuracy by treating the model as a black box. Explanations such as sparse linear models [11] (henceforth called linear LIME) or gradients [2, 10] can still exhibit high precision and low effort (which are de-facto requirements, as there is little point in explaining a model if explanations lead to poor understanding or are too complex) even for very complex models by providing explanations that are local in their scope (i.e.

Models obtained by decision tree induction techniques excel in being interpretable.However, they can be prone to overfitting, which results in a low predictive performance. Ensemble techniques are able to achieve a higher accuracy. However, this comes at a cost of losing interpretability of the resulting model. This makes ensemble techniques impractical in applications where decision support, instead of decision making, is crucial. To bridge this gap, we present the GENESIM algorithm that transforms an ensemble of decision trees to a single decision tree with an enhanced predictive performance by using a genetic algorithm. We compared GENESIM to prevalent decision tree induction and ensemble techniques using twelve publicly available data sets. The results show that GENESIM achieves a better predictive performance on most of these data sets than decision tree induction techniques and a predictive performance in the same order of magnitude as the ensemble techniques. Moreover, the resulting model of GENESIM has a very low complexity, making it very interpretable, in contrast to ensemble techniques.

In this letter, a novel weighted ensemble classifier is proposed that improves classification accuracy and minimizes the number of classifiers. Ensemble weight finding problem is modeled as a cost function with following terms: (a) a data fidelity term aiming to decrease misclassification rate, (b) a sparsity term aiming to decrease the number of classifiers, and (c) a non-negativity constraint on the weights of the classifiers. The proposed cost function is a non-convex and hard to solve; thus, convex relaxation techniques and novel approximations are employed to obtain a numerically efficient solution. The proposed method achieves better or similar performance compared to state-of-the art classifier ensemble methods, while using lower number of classifiers.

Recent discussion in the public sphere about algorithmic classification has involved tension between competing notions of what it means for a probabilistic classification to be fair to different groups. We formalize three fairness conditions that lie at the heart of these debates, and we prove that except in highly constrained special cases, there is no method that can satisfy these three conditions simultaneously. Moreover, even satisfying all three conditions approximately requires that the data lie in an approximate version of one of the constrained special cases identified by our theorem. These results suggest some of the ways in which key notions of fairness are incompatible with each other, and hence provide a framework for thinking about the trade-offs between them.

In this paper, we investigate the recovery of a sparse weight vector (parameters vector) from a set of noisy linear combinations. However, only partial information about the matrix representing the linear combinations is available. Assuming a low-rank structure for the matrix, one natural solution would be to first apply a matrix completion on the data, and then to solve the resulting compressed sensing problem. In big data applications such as massive MIMO and medical data, the matrix completion step imposes a huge computational burden. Here, we propose to reduce the computational cost of the completion task by ignoring the columns corresponding to zero elements in the sparse vector. To this end, we employ a technique to initially approximate the support of the sparse vector. We further propose to unify the partial matrix completion and sparse vector recovery into an augmented four-step problem. Simulation results reveal that the augmented approach achieves the best performance, while both proposed methods outperform the natural two-step technique with substantially less computational requirements.

Other bigger lists (sometimes created by robots) can be found here and are usually based on your Klout score, which in my opinion is not accurate. The list below is truly original and I would even add, somewhat unexpected, as you won't find Bernard Marr, Kirk Borne and other well known gurus. Just in case you're wondering, @FILWD stands for Fell In Love With Data, which happens to be the name of Enrico Bertini's blog. While the Assistant Professor at NYU doesn't talk much on Twitter himself, he uses the platform very effectively to share news and insights about data visualizations and adds his highly-valued opinions. Like Rob Thomas, Enrico's a great follow if you want a well-balanced stream of data-speak and general life observations.