Multi-omic data provides multiple views of the same patients. Integrative analysis of multi-omic data is crucial to elucidate the molecular underpinning of disease etiology. However, multi-omic data has the "big p, small N" problem (the number of features is large, but the number of samples is small), it is challenging to train a complicated machine learning model from the multi-omic data alone and make it generalize well. Here we propose a framework termed Multi-view Factorization AutoEncoder with network constraints to integrate multi-omic data with domain knowledge (biological interactions networks). Our framework employs deep representation learning to learn feature embeddings and patient embeddings simultaneously, enabling us to integrate feature interaction network and patient view similarity network constraints into the training objective. The whole framework is end-to-end differentiable. We applied our approach to the TCGA Pan-cancer dataset and achieved satisfactory results to predict disease progression-free interval (PFI) and patient overall survival (OS) events. Code will be made publicly available.

With online calendar services gaining popularity worldwide, calendar data has become one of the richest context sources for understanding human behavior. However, event scheduling is still time-consuming even with the development of online calendars. Although machine learning based event scheduling models have automated scheduling processes to some extent, they often fail to understand subtle user preferences and complex calendar contexts with event titles written in natural language. In this paper, we propose Neural Event Scheduling Assistant (NESA) which learns user preferences and understands calendar contexts, directly from raw online calendars for fully automated and highly effective event scheduling. We leverage over 593K calendar events for NESA to learn scheduling personal events, and we further utilize NESA for multi-attendee event scheduling. NESA successfully incorporates deep neural networks such as Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Highway Network for learning the preferences of each user and understanding calendar context based on natural languages. The experimental results show that NESA significantly outperforms previous baseline models in terms of various evaluation metrics on both personal and multi-attendee event scheduling tasks. Our qualitative analysis demonstrates the effectiveness of each layer in NESA and learned user preferences.

Lipschitz regularized neural networks augment the usual fidelity term used in training with a regularization term corresponding the excess Lipschitz constant of the network compared to the Lipschitz constant of the data. We prove that Lipschitz regularized neural networks converge, and provide a rate, in the limit as the number of data points $n\to\infty$. We consider the regime where perfect fitting of data is possible, which means the size of the network grows with $n$. There are two regimes: in the case of perfect labels, we prove convergence to the label function which corresponds to zero loss. In the case of corrupted labels which occurs when the Lipschitz constant of the data blows up, we prove convergence to a regularized label function which is the solution of a limiting variational problem.

A friend of mine who is about to start a career in artificial intelligence research recently asked what I wish I had known when I started two years ago. Below are some lessons I have learned so far. They range from general life lessons to relatively specific tricks of the AI trade. I hope others find them useful. I was initially very intimidated by my colleagues and hesitant to ask basic questions that might betray my lack of expertise. It was many months before I felt comfortable enough with a few colleagues to ask questions, and still my questions were carefully formulated.

Question answering is an important task for autonomous agents and virtual assistants alike and was shown to support the disabled in efficiently navigating an overwhelming environment. Many existing methods focus on observation-based questions, ignoring our ability to seamlessly combine observed content with general knowledge. To understand interactions with a knowledge base, a dataset has been introduced recently and keyword matching techniques were shown to yield compelling results despite being vulnerable to misconceptions due to synonyms and homographs. To address this issue, we develop a learning-based approach which goes straight to the facts via a learned embedding space. We demonstrate state-of-the-art results on the challenging recently introduced fact-based visual question answering dataset, outperforming competing methods by more than 5%.

Abstract--Accurate and automated detection of anomalous samples in a natural image dataset can be accomplished with a probabilistic model for end-to-end modeling of images. Such images have heterogeneous complexity, however, and a probabilistic model overlooks simply shaped objects with small anomalies. This is because the probabilistic model assigns undesirably lower likelihoods to complexly shaped objects that are nevertheless consistent with set standards. To overcome this difficulty, we propose an unregularized score for deep generative models (DGMs), which are generative models leveraging deep neural networks. We found that the regularization terms of the DGMs considerably influence the anomaly score depending on the complexity of the samples. By removing these terms, we obtain an unregularized score, which we evaluated on a toy dataset and real-world manufacturing datasets. Empirical results demonstrate that the unregularized score is robust to the inherent complexity of samples and can be used to better detect anomalies. Image-based anomaly detection has recently attracted considerable attention in the field of machine learning. This technique can be used to detect pedestrians behaving abnormally from surveillance video in order to prevent accidents [1], [2], or to detect lesions in medical images to provide early diagnosis [3]. In manufacturing plants, moreover, image-based anomaly detection can reject products not coincident with set standards.

The ability to conduct logical reasoning is a fundamental aspect of intelligent behavior, and thus an important problem along the way to human-level artificial intelligence. Traditionally, symbolic methods from the field of knowledge representation and reasoning have been used to equip agents with capabilities that resemble human logical reasoning qualities. More recently, however, there has been an increasing interest in using machine learning rather than logic-based formalisms to tackle these tasks. In this paper, we employ state-of-the-art methods for training deep neural networks to devise a novel model that is able to learn how to effectively perform basic ontology reasoning. This is an important and at the same time very natural reasoning problem, which is why the presented approach is applicable to a plethora of important real-world problems. We present the outcomes of several experiments, which show that our model learned to perform precise reasoning on diverse and challenging tasks. Furthermore, it turned out that the suggested approach suffers much less from different obstacles that prohibit symbolic reasoning, and, at the same time, is surprisingly plausible from a biological point of view.

As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this work, we propose an OOD detection algorithm which comprises of an ensemble of classifiers. We train each classifier in a self-supervised manner by leaving out a random subset of training data as OOD data and the rest as in-distribution (ID) data. We propose a novel margin-based loss over the softmax output which seeks to maintain at least a margin m between the average entropy of the OOD and in-distribution samples. In conjunction with the standard cross-entropy loss, we minimize the novel loss to train an ensemble of classifiers. We also propose a novel method to combine the outputs of the ensemble of classifiers to obtain OOD detection score and class prediction. Overall, our method convincingly outperforms Hendrycks et al. [7] and the current state-of-the-art ODIN [13] on several OOD detection benchmarks.

A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art results in various environments. We also train our agent entirely inside of an environment generated by its own internal world model, and transfer this policy back into the actual environment. Interactive version of paper at https://worldmodels.github.io

Although stochastic gradient descent (SGD) method and its variants (e.g., stochastic momentum methods, AdaGrad) are the choice of algorithms for solving non-convex problems (especially deep learning), there still remain big gaps between the theory and the practice with many questions unresolved. For example, there is still a lack of theories of convergence for SGD and its variants that use stagewise step size and return an averaged solution in practice. In addition, theoretical insights of why adaptive step size of AdaGrad could improve non-adaptive step size of {\sgd} is still missing for non-convex optimization. This paper aims to address these questions and fill the gap between theory and practice. We propose a universal stagewise optimization framework for a broad family of {\bf non-smooth non-convex} (namely weakly convex) problems with the following key features: (i) at each stage any suitable stochastic convex optimization algorithms (e.g., SGD or AdaGrad) that return an averaged solution can be employed for minimizing a regularized convex problem; (ii) the step size is decreased in a stagewise manner; (iii) an averaged solution is returned as the final solution that is selected from all stagewise averaged solutions with sampling probabilities {\it increasing} as the stage number. Our theoretical results of stagewise AdaGrad exhibit its adaptive convergence, therefore shed insights on its faster convergence for problems with sparse stochastic gradients than stagewise SGD. To the best of our knowledge, these new results are the first of their kind for addressing the unresolved issues of existing theories mentioned earlier.