Between the four of us, we have studied at Stanford, IIM Ahmedabad, the IITs and have spent years (decades, actually) working in tech, in the Bay Area, New York, Singapore and Bangalore. We think we might have hit upon a neat way of teaching complicated tech courses in a funny, practical, engaging way, which is why we are so excited to be here on Udemy! We hope you will try our offerings, and think you'll like them:-)

"Due to the recent achievements of artificial neural networks across many different tasks (such as face recognition, object detection and Go), deep learning has become extremely popular. This post aims to be a starting point for those interested in learning more about it. If you already have a basic understanding of linear algebra, calculus, probability and programming: I recommend starting with Stanford's CS231n. The course notes are comprehensive and well-written. The slides for each lesson are also available, and even though the accompanying videos were removed from the official site, re-uploads are quite easy to find online. If you don't have the relevant math background: There is an incredible amount of free material online that can be used to learn the required math knowledge. Gilbert Strang's course on linear algebra is a great introduction to the field. For the other subjects, edX has courses from MIT on both calculus and probability. If you are interested in learning more about machine learning: Andrew Ng's Coursera class is a popular choice as a first class in machine learning. There are other great options available such as Yaser Abu-Mostafa's machine learning course which focuses much more on theory than the Coursera class but it is still relevant for beginners. Knowledge in machine learning isn't really a prerequisite to learning deep learning, but it does help. In addition, learning classical machine learning and not only deep learning is important because it provides a theoretical background and because deep learning isn't always the correct solution. Geoffrey Hinton's Coursera class "Neural Networks for Machine Learn... covers a lot of different topics, and so does Hugo Larochelle's "Neural Networks Class".

From a sequence of similarity networks, with edges representing certain similarity measures between nodes, we are interested in detecting a change-point which changes the statistical property of the networks. After the change, a subset of anomalous nodes which compares dissimilarly with the normal nodes. We study a simple sequential change detection procedure based on node-wise average similarity measures, and study its theoretical property. Simulation and real-data examples demonstrate such a simply stopping procedure has reasonably good performance. We further discuss the faulty sensor isolation (estimating anomalous nodes) using community detection.

Community detection has become very popular in network analysis the last decades. Its range of applications include social sciences, biology and complex systems, such as the worldwide-web, protein-protein interactions, or social networks (see [5] for a thorough exposition of the topic). To tackle this problem, spectral approaches have been introduced in [12] or [18], inspired from the so-called spectral clustering problem (see [10]). However, the treatment of larger and larger graphs has been investigated and modularity-based algorithms has been proposed. This class of algorithms maximize a quality index called modularity, introduced in [13].

We are interested in learning customers' video preferences from their historic viewing patterns and geographical location. We consider a Bayesian latent factor modeling approach for this task. In order to tune the complexity of the model to best represent the data, we make use of Bayesian nonparameteric techniques. We describe an inference technique that can scale to large real-world data sets. Finally we show results obtained by applying the model to a large internal Netflix data set, that illustrates that the model was able to capture interesting relationships between viewing patterns and geographical location.

James Weatherall Advanced Analytics Centre, Global Medicines Development, AstraZeneca james.weatherall@astrazeneca.com We study information theoretic methods for ranking biomarkers. In clinical trials there are two, closely related, types of biomarkers: predictive and prognostic, and disentangling them is a key challenge. Our first step is to phrase biomarker ranking in terms of optimizing an information theoretic quantity. This formalization of the problem will enable us to derive rankings of predictive/prognostic biomarkers, by estimating different, high dimensional, conditional mutual information terms. To estimate these terms, we suggest efficient low dimensional approximations, and we derive an empirical Bayes estimator, which is suitable for small or sparse datasets. Finally, we introduce a new visualisation tool that captures the prognostic and the predictive strength of a set of biomarkers. We believe this representation will prove to be a powerful tool in biomarker discovery.

In this paper, we consider the problem of event classification with multi-variate time series data consisting of heterogeneous (continuous and categorical) variables. The complex temporal dependencies between the variables combined with sparsity of the data makes the event classification problem particularly challenging. Most state-of-art approaches address this either by designing hand-engineered features or breaking up the problem over homogeneous variates. In this work, we propose and compare three representation learning algorithms over symbolized sequences which enables classification of heterogeneous time-series data using a deep architecture. The proposed representations are trained jointly along with the rest of the network architecture in an end-to-end fashion that makes the learned features discriminative for the given task. Experiments on three real-world datasets demonstrate the effectiveness of the proposed approaches.

Accurately predicting drug responses to cancer is an important problem hindering oncologists' efforts to find the most effective drugs to treat cancer, which is a core goal in precision medicine. The scientific community has focused on improving this prediction based on genomic, epigenomic, and proteomic datasets measured in human cancer cell lines. Real-world cancer cell lines contain noise, which degrades the performance of machine learning algorithms. This problem is rarely addressed in the existing approaches. In this paper, we present a noise-filtering approach that integrates techniques from numerical linear algebra and information retrieval targeted at filtering out noisy cancer cell lines. By filtering out noisy cancer cell lines, we can train machine learning algorithms on better quality cancer cell lines. We evaluate the performance of our approach and compare it with an existing approach using the Area Under the ROC Curve (AUC) on clinical trial data. The experimental results show that our proposed approach is stable and also yields the highest AUC at a statistically significant level.

Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks. Our learning algorithm simultaneously learns a compiled inference network and the generative model, leveraging a structured variational approximation parameterized by recurrent neural networks to mimic the posterior distribution. We apply the learning algorithm to both synthetic and real-world datasets, demonstrating its scalability and versatility. We find that using the structured approximation to the posterior results in models with significantly higher held-out likelihood.

This research evaluates the performance of an Artificial Neural Network based prediction system that was employed on the Shanghai Stock Exchange for the period 21-Sep-2016 to 11-Oct-2016. It is a follow-up to a previous paper in which the prices were predicted and published before September 21. Stock market price prediction remains an important quest for investors and researchers. This research used an Artificial Intelligence system, being an Artificial Neural Network that is feedforward multi-layer perceptron with error backpropagation for prediction, unlike other methods such as technical, fundamental or time series analysis. While these alternative methods tend to guide on trends and not the exact likely prices, neural networks on the other hand have the ability to predict the real value prices, as was done on this research. Nonetheless, determination of suitable network parameters remains a challenge in neural network design, with this research settling on a configuration of 5:21:21:1 with 80% training data or 4-year of training data as a good enough model for stock prediction, as already determined in a previous research by the author. The comparative results indicate that neural network can predict typical stock market prices with mean absolute percentage errors that are as low as 1.95% over the ten prediction instances that was studied in this research.