We view the Information Bottleneck Principle (IBP: Tishby et al., 1999; Schwartz-Ziv and Tishby, 2017) and Predictive Information Bottleneck Principle (PIBP: Still et al., 2007; Alemi, 2019) as special cases of a family of general information bottleneck objectives (IBOs). Each IBO corresponds to a particular constrained optimization problem where the constraints apply to: (a) the mutual information between the training data and the learned model parameters or extracted representation of the data, and (b) the mutual information between the learned model parameters or extracted representation of the data and the test data (if any). The heuristics behind the IBP and PIBP are shown to yield different constraints in the corresponding constrained optimization problem formulations. We show how other heuristics lead to a new IBO, different from both the IBP and PIBP, and use the techniques from (Alemi, 2019) to derive and optimize a variational upper bound on the new IBO. We then apply the theory of general IBOs to resolve the seeming contradiction between, on the one hand, the recommendations of IBP and PIBP to maximize the mutual information between the model parameters and test data, and on the other, recent information-theoretic results (see Xu and Raginsky, 2017) suggesting that this mutual information should be minimized. The key insight is that the heuristics (and thus the constraints in the constrained optimization problems) of IBP and PIBP are not applicable to the scenario analyzed by (Xu and Raginsky, 2017) because the latter makes the additional assumption that the parameters of the trained model have been selected to minimize the empirical loss function. Aided by this insight, we formulate a new IBO that accounts for this property of the parameters of the trained model, and derive and optimize a variational bound on this IBO.

We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and action spaces than those of traditional 1v1 games, such as Go and Atari series, which makes it very difficult to search any policies with human-level performance. In this paper, we present a deep reinforcement learning framework to tackle this problem from the perspectives of both system and algorithm. Our system is of low coupling and high scalability, which enables efficient explorations at large scale. Our algorithm includes several novel strategies, including control dependency decoupling, action mask, target attention, and dual-clip PPO, with which our proposed actor-critic network can be effectively trained in our system. Tested on the MOBA game Honor of Kings, the trained AI agents can defeat top professional human players in full 1v1 games. Introduction Deep reinforcement learning (DRL) has been widely used for building agents to learn complex control in competitive environments. In the competitive setting, a considerable amount of existing DRL research adopt two-agent games as the testbed, i.e., one agent versus another (1v1). Among them, Atari series and board games have been widely studied. For example, a human-level agent for playing Atari games is trained with deep Q-networks (Mnih et al. 2015). The incorporation of supervised learning and self-play into the training brings the agent to the level of beating human professionals in the game of Go (Silver et al. 2016).

Understanding search queries is critical for shopping search engines to deliver a satisfying customer experience. Popular shopping search engines receive billions of unique queries yearly, each of which can depict any of hundreds of user preferences or intents. In order to get the right results to customers it must be known queries like "inexpensive prom dresses" are intended to not only surface results of a certain product type but also products with a low price. Referred to as query intents, examples also include preferences for author, brand, age group, or simply a need for customer service. Recent works such as BERT have demonstrated the success of a large transformer encoder architecture with language model pre-training on a variety of NLP tasks. We adapt such an architecture to learn intents for search queries and describe methods to account for the noisiness and sparseness of search query data. We also describe cost effective ways of hosting transformer encoder models in context with low latency requirements. With the right domain-specific training we can build a shareable deep learning model whose internal representation can be reused for a variety of query understanding tasks including query intent identification. Model sharing allows for fewer large models needed to be served at inference time and provides a platform to quickly build and roll out new search query classifiers.

Systems powered by artificial intelligence are being developed to be more user-friendly by communicating with users in a progressively human-like conversational way. Chatbots, also known as dialogue systems, interactive conversational agents, or virtual agents are an example of such systems used in a wide variety of applications ranging from customer support in the business domain to companionship in the healthcare sector. It is becoming increasingly important to develop chatbots that can best respond to the personalized needs of their users so that they can be as helpful to the user as possible in a real human way. This paper investigates and compares three popular existing chatbots API offerings and then propose and develop a voice interactive and multilingual chatbot that can effectively respond to users mood, tone, and language using IBM Watson Assistant, Tone Analyzer, and Language Translator. The chatbot was evaluated using a use case that was targeted at responding to users needs regarding exam stress based on university students survey data generated using Google Forms. The results of measuring the chatbot effectiveness at analyzing responses regarding exam stress indicate that the chatbot responding appropriately to the user queries regarding how they are feeling about exams 76.5%. The chatbot could also be adapted for use in other application areas such as student info-centers, government kiosks, and mental health support systems.

Management Information Systems Department, T.C. Kadir Has University, Istanbul, T urkey Abstract Behavior of a malware varies with respect to malware types. Therefore, knowing type of a malware affects strategies of system protection softwares. Many malware type classification models empowered by machine and deep learning achieve superior accuracies to predict malware types. Machine learning based models need to do heavy feature engineering and feature engineering is dominantly effecting performance of models. On the other hand, deep learning based models require less feature engineering than machine learning based models. However, traditional deep learning architectures and components cause very complex and data sensitive models. This paper proposes an ensemble capsule network model based on bootstrap aggregating technique. The proposed method are tested on two malware datasets, whose the-state-of-the-art results are well-known.

Recent work suggests goal-driven training of neural networks can be used to model neural activity in the brain. While response properties of neurons in artificial neural networks bear similarities to those in the brain, the network architectures are often constrained to be different. Here we ask if a neural network can recover both neural representations and, if the architecture is unconstrained and optimized, the anatomical properties of neural circuits. We demonstrate this in a system where the connectivity and the functional organization have been characterized, namely, the head direction circuits of the rodent and fruit fly. We trained recurrent neural networks (RNNs) to estimate head direction through integration of angular velocity. We found that the two distinct classes of neurons observed in the head direction system, the Ring neurons and the Shifter neurons, emerged naturally in artificial neural networks as a result of training. Furthermore, connectivity analysis and in-silico neurophysiology revealed structural and mechanistic similarities between artificial networks and the head direction system. Overall, our results show that optimization of RNNs in a goal-driven task can recapitulate the structure and function of biological circuits, suggesting that artificial neural networks can be used to study the brain at the level of both neural activity and anatomical organization.

Machine learning algorithms for generating molecular structures offer a promising new approach to drug discovery. We cast molecular optimization as a translation problem, where the goal is to map an input compound to a target compound with improved biochemical properties. Remarkably, we observe that when generated molecules are iteratively fed back into the translator, molecular compound attributes improve with each step. We show that this finding is invariant to the choice of translation model, making this a "black box" algorithm. We call this method Black Box Recursive Translation (BBRT), a new inference method for molecular property optimization. This simple, powerful technique operates strictly on the inputs and outputs of any translation model. We obtain new state-of-the-art results for molecular property optimization tasks using our simple drop-in replacement with well-known sequence and graph-based models. Our method provides a significant boost in performance relative to its non-recursive peers with just a simple "for" loop. Further, BBRT is highly interpretable, allowing users to map the evolution of newly discovered compounds from known starting points.

Over the last twenty five years, advances in the collection and analysis of fMRI data have enabled new insights into the brain basis of human health and disease. Individual behavioral variation can now be visualized at a neural level as patterns of connectivity among brain regions. Functional brain imaging is enhancing our understanding of clinical psychiatric disorders by revealing ties between regional and network abnormalities and psychiatric symptoms. Initial success in this arena has recently motivated collection of larger datasets which are needed to leverage fMRI to generate brain-based biomarkers to support development of precision medicines. Despite methodological advances and enhanced computational power, evaluating the quality of fMRI scans remains a critical step in the analytical framework. Before analysis can be performed, expert reviewers visually inspect raw scans and preprocessed derivatives to determine viability of the data. This Quality Control (QC) process is labor intensive, and the inability to automate at large scale has proven to be a limiting factor in clinical neuroscience fMRI research. We present a novel method for automating the QC of fMRI scans. We train machine learning classifiers using features derived from brain MR images to predict the "quality" of those images, based on the ground truth of an expert's opinion. We emphasize the importance of these classifiers' ability to generalize their predictions across data from different studies. To address this, we propose a novel approach entitled "FMRI preprocessing Log mining for Automated, Generalizable Quality Control" (FLAG-QC), in which features derived from mining runtime logs are used to train the classifier. We show that classifiers trained on FLAG-QC features perform much better (AUC=0.79) than previously proposed feature sets (AUC=0.56) when testing their ability to generalize across studies.

The optimization of multilayer neural networks typically leads to a solution with zero training error, yet the landscape can exhibit spurious local minima and the minima can be disconnected. In this paper, we shed light on this phenomenon: we show that the combination of stochastic gradient descent (SGD) and over-parameterization makes the landscape of multilayer neural networks approximately connected and thus more favorable to optimization. More specifically, we prove that SGD solutions are connected via a piecewise linear path, and the increase in loss along this path vanishes as the number of neurons grows large. This result is a consequence of the fact that the parameters found by SGD are increasingly dropout stable as the network becomes wider. We show that, if we remove part of the neurons (and suitably rescale the remaining ones), the change in loss is independent of the total number of neurons, and it depends only on how many neurons are left. Our results exhibit a mild dependence on the input dimension: they are dimension-free for two-layer networks and depend linearly on the dimension for multilayer networks. We validate our theoretical findings with numerical experiments for different architectures and classification tasks.

Auto-encoding and generative models have made tremendous successes in image and signal representation learning and generation. These models, however, generally employ the full Euclidean space or a bounded subset (such as $[0,1]^l$) as the latent space, whose flat geometry is often too simplistic to meaningfully reflect the topological structure of the data. This paper aims at exploring a universal geometric structure of the latent space for better data representation. Inspired by differential geometry, we propose a Chart Auto-Encoder (CAE), which captures the manifold structure of the data with multiple charts and transition functions among them. CAE translates the mathematical definition of manifold through parameterizing the entire data set as a collection of overlapping charts, creating local latent representations. These representations are an enhancement of the single-charted latent space commonly employed in auto-encoding models, as they reflect the intrinsic structure of the manifold. Therefore, CAE achieves a more accurate approximation of data and generates realistic synthetic examples. We demonstrate the efficacy of CAEs through a series experiments with synthetic and real-life data which illustrate that CAEs can out-preform variational auto-encoders on reconstruction tasks while using much smaller latent spaces.