Accelerating System Log Processing by Semi-supervised Learning: A Technical Report
There is an increasing need for more automated system-log analysis tools for large scale online system in a timely manner. However, conventional way to monitor and classify the log output based on keyword list does not scale well for complex system in which codes contributed by a large group of developers, with diverse ways of encoding the error messages, often with misleading pre-set labels. In this paper, we propose that the design of a large scale online log analysis should follow the ‘Least Prior Knowledge Principle’, in which unsupervised or semi-supervised solution with the minimal prior knowledge of the log should be encoded directly. Thereby, we report our experience in designing a two-stage machine learning based method, in which the system logs are regarded as the output of a quasi-natural language, pre-filtered by a perplexity score threshold, and then undergo a fine-grained classification procedure. Tests on empirical data show that our method has obvious advantage regarding to the processing speed and classification accuracy.
Anomaly Detection in Paleoclimate Records using Information Theory
The Shannon entropy rate can be useful in identifying anomalies in high-resolution paleoclimate data records, including noise, outliers, and post-processing issues. We demonstrate this using calculations of weighted permutation entropy (WPE) on water-isotope records in a deep polar ice core. In one region of the isotope records, WPE calculations revealed a significant jump in the amount of new information present in the time series at each point. We conjectured that this effect was due to noise introduced by an older laboratory instrument. In this paper, we validate that conjecture by re-analyzing a section of the ice core using a more-advanced version of the laboratory instrument. The anomalous noise levels are absent from the WPE trace of the new data. In other sections of the core, we show that WPE can be used to identify anomalies in the raw data that are not associated with climatic or glaciological processes, but rather effects occurring during ice sampling, analysis, or data post-processing. These examples make it clear that WPE is a useful forensic tool for identifying sections of data that requires targeted re-analysis, or even a wholly new data set.
ColNet: Embedding the Semantics of Web Tables for Column Type Prediction
Automatically annotating column types with knowledge base (KB) concepts is a critical task to gain a basic understanding of web tables. Current methods rely on either table metadata like column name or entity correspondences of cells in the KB, and may fail to deal with growing web tables with incomplete meta information. In this paper we propose a neural network based column type annotation framework named ColNet which is able to integrate KB reasoning and lookup with machine learning and can automatically train Convolutional Neural Networks for prediction. The prediction model not only considers the contextual semantics within a cell using word representation, but also embeds the semantic of a column by learning locality features from multiple cells. The method is evaluated with DBPedia and two different web table datasets, T2Dv2 from the general Web and Limaye from Wikipedia pages, and achieves higher performance than the state-of-the-art approaches.
Detecting Structural Changes in Longitudinal Network Data
Dynamic modeling of longitudinal networks has been an increasingly important topic in applied research. While longitudinal network data commonly exhibit dramatic changes in its structures, existing methods have largely focused on modeling smooth topological changes over time. In this paper, we develop a hidden Markov multilinear tensor model (HMTM) that combines the multilinear tensor regression model (Hoff 2011) with a hidden Markov model using Bayesian inference. We model changes in network structure as shifts in discrete states yielding particular sets of network generating parameters. Our simulation results demonstrate that the proposed method correctly detects the number, locations, and types of changes in latent node characteristics. We apply the proposed method to international military alliance networks to find structural changes in the coalition structure among nations.
Explaining Explanations in AI
Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might break. However, when considering any such model it’s important to remember Box’s maxim that ‘All models are wrong but some are useful.’ We focus on the distinction between these models and explanations in philosophy and sociology. These models can be understood as a ‘do it yourself kit’ for explanations, allowing a practitioner to directly answer ‘what if questions’ or generate contrastive explanations without external assistance. Although a valuable ability, giving these models as explanations appears more difficult than necessary, and other forms of explanation may not have the same trade-offs. We contrast the different schools of thought on what makes an explanation, and suggest that machine learning might benefit from viewing the problem more broadly.
Deep Metric Learning by Online Soft Mining and Class-Aware Attention
Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large fraction of trivial samples. Therefore, most existing methods generally resort to sample mining strategies for selecting nontrivial samples to accelerate convergence and improve performance. In this work, we identify two critical limitations of the sample mining methods, and provide solutions for both of them. First, previous mining methods assign one binary score to each sample, i.e., dropping or keeping it, so they only selects a subset of relevant samples in a mini-batch. Therefore, we propose a novel sample mining method, called Online Soft Mining (OSM), which assigns one continuous score to each sample to make use of all samples in the mini-batch. OSM learns extended manifolds that preserve useful intraclass variances by focusing on more similar positives. Second, the existing methods are easily influenced by outliers as they are generally included in the mined subset. To address this, we introduce Class-Aware Attention (CAA) that assigns little attention to abnormal data samples. Furthermore, by combining OSM and CAA, we propose a novel weighted contrastive loss to learn discriminative embeddings. Extensive experiments on two fine-grained visual categorisation datasets and two video-based person re-identification benchmarks show that our method significantly outperforms the state-of-the-art.
Bias Disparity in Recommendation Systems
Recommender systems have been applied successfully in a number of different domains, such as, entertainment, commerce, and employment. Their success lies in their ability to exploit the collective behavior of users in order to deliver highly targeted, personalized recommendations. Given that recommenders learn from user preferences, they incorporate different biases that users exhibit in the input data. More importantly, there are cases where recommenders may amplify such biases, leading to the phenomenon of bias disparity. In this short paper, we present a preliminary experimental study on synthetic data, where we investigate different conditions under which a recommender exhibits bias disparity, and the long-term effect of recommendations on data bias. We also consider a simple re-ranking algorithm for reducing bias disparity, and present some observations for data disparity on real data.
Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference
The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data. Although ML-based solutions address the efficient computing requirements of big data, they introduce (new) security vulnerabilities into the systems, which cannot be addressed by traditional monitoring-based security measures. Therefore, this paper first presents a brief overview of various security threats in machine learning, their respective threat models and associated research challenges to develop robust security measures. To illustrate the security vulnerabilities of ML during training, inferencing and hardware implementation, we demonstrate some key security threats on ML using LeNet and VGGNet for MNIST and German Traffic Sign Recognition Benchmarks (GTSRB), respectively. Moreover, based on the security analysis of ML-training, we also propose an attack that has a very less impact on the inference accuracy. Towards the end, we highlight the associated research challenges in developing security measures and provide a brief overview of the techniques used to mitigate such security threats.
Transfer learning for time series classification
Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network’s weights) to a second network to be trained on a target dataset. This idea has been shown to improve deep neural network’s generalization capabilities in many computer vision tasks such as image recognition and object localization. Apart from these applications, deep Convolutional Neural Networks (CNNs) have also recently gained popularity in the Time Series Classification (TSC) community. However, unlike for image recognition problems, transfer learning techniques have not yet been investigated thoroughly for the TSC task. This is surprising as the accuracy of deep learning models for TSC could potentially be improved if the model is fine-tuned from a pre-trained neural network instead of training it from scratch. In this paper, we fill this gap by investigating how to transfer deep CNNs for the TSC task. To evaluate the potential of transfer learning, we performed extensive experiments using the UCR archive which is the largest publicly available TSC benchmark containing 85 datasets. For each dataset in the archive, we pre-trained a model and then fine-tuned it on the other datasets resulting in 7140 different deep neural networks. These experiments revealed that transfer learning can improve or degrade the model’s predictions depending on the dataset used for transfer. Therefore, in an effort to predict the best source dataset for a given target dataset, we propose a new method relying on Dynamic Time Warping to measure inter-datasets similarities. We describe how our method can guide the transfer to choose the best source dataset leading to an improvement in accuracy on 71 out of 85 datasets.
Task Embedded Coordinate Update: A Realizable Framework for Multivariate Non-convex Optimization
We in this paper propose a realizable framework TECU, which embeds task-specific strategies into update schemes of coordinate descent, for optimizing multivariate non-convex problems with coupled objective functions. On one hand, TECU is capable of improving algorithm efficiencies through embedding productive numerical algorithms, for optimizing univariate sub-problems with nice properties. From the other side, it also augments probabilities to receive desired results, by embedding advanced techniques in optimizations of realistic tasks. Integrating both numerical algorithms and advanced techniques together, TECU is proposed in a unified framework for solving a class of non-convex problems. Although the task embedded strategies bring inaccuracies in sub-problem optimizations, we provide a realizable criterion to control the errors, meanwhile, to ensure robust performances with rigid theoretical analyses. By respectively embedding ADMM and a residual-type CNN in our algorithm framework, the experimental results verify both efficiency and effectiveness of embedding task-oriented strategies in coordinate descent for solving practical problems.
GEMRank: Global Entity Embedding For Collaborative Filtering
Recently, word embedding algorithms have been applied to map the entities of recommender systems, such as users and items, to new feature spaces using textual element-context relations among them. Unlike many other domains, this approach has not achieved a desired performance in collaborative filtering problems, probably due to unavailability of appropriate textual data. In this paper we propose a new recommendation framework, called GEMRank that can be applied when the user-item matrix is the sole available souce of information. It uses the concept of profile co-occurrence for defining relations among entities and applies a factorization method for embedding the users and items. GEMRank then feeds the extracted representations to a neural network model to predict user-item like/dislike relations which the final recommendations are made based on. We evaluated GEMRank in an extensive set of experiments against state of the art recommendation methods. The results show that GEMRank significantly outperforms the baseline algorithms in a variety of data sets with different degrees of density.
Collaboration and integration through information technologies in supply chains
Supply chain management encompasses various processes including various conventional logistics activities, and various other processes These processes are supported — to a certain limit — by coordination and integration mechanisms which are long-term strategies that give competitive advantage through overall supply chain efficiency. Information Technology, by the way of collecting, sharing and gathering data, exchanging information, optimising process through package software, is becoming one of the key developments and success of these collaboration strategies. This paper proposes a study to identify the methods used for collaborative works in the supply chain and focuses on some of its areas, as between a company and its suppliers (i.e., inventory sharing) and its customers (i.e., customer demand, forecasting), and also the integration of product information in the value chain.
How deep is deep enough? – Optimizing deep neural network architecture
Deep neural networks use stacked layers of feature detectors to repeatedly transform the input data, so that structurally different classes of input become well separated in the final layer. While the method has turned out extremely powerful in many applications, its success depends critically on the correct choice of hyperparameters, in particular the number of network layers. Here, we introduce a new measure, called the generalized discrimination value (GDV), which quantifies how well different object classes separate in each layer. Due to its definition, the GDV is invariant to translation and scaling of the input data, independent of the number of features, as well as independent of the number and permutation of the neurons within a layer. We compute the GDV in each layer of a Deep Belief Network that was trained unsupervised on the MNIST data set. Strikingly, we find that the GDV first improves with each successive network layer, but then gets worse again beyond layer 30, thus indicating the optimal network depth for this data classification task. Our further investigations suggest that the GDV can serve as a universal tool to determine the optimal number of layers in deep neural networks for any type of input data.
Structured Neural Summarization
Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, we develop a framework to extend existing sequence encoders with a graph component that can reason about long-distance relationships in weakly structured data such as text. In an extensive evaluation, we show that the resulting hybrid sequence-graph models outperform both pure sequence models as well as pure graph models on a range of summarization tasks.
Multi-layer Relation Networks
Relational Networks (RN) as introduced by Santoro et al. (2017) have demonstrated strong relational reasoning capabilities with a rather shallow architecture. Its single-layer design, however, only considers pairs of information objects, making it unsuitable for problems requiring reasoning across a higher number of facts. To overcome this limitation, we propose a multi-layer relation network architecture which enables successive refinements of relational information through multiple layers. We show that the increased depth allows for more complex relational reasoning by applying it to the bAbI 20 QA dataset, solving all 20 tasks with joint training and surpassing the state-of-the-art results.
Deep Genetic Network
Optimizing a neural network’s performance is a tedious and time taking process, this iterative process does not have any defined solution which can work for all the problems. Optimization can be roughly categorized into – Architecture and Hyperparameter optimization. Many algorithms have been devised to address this problem. In this paper we introduce a neural network architecture (Deep Genetic Network) which will optimize its parameters during training based on its fitness. Deep Genetic Net uses genetic algorithms along with deep neural networks to address the hyperparameter optimization problem, this approach uses ideas like mating and mutation which are key to genetic algorithms which help the neural net architecture to learn to optimize its hyperparameters by itself rather than depending on a person to explicitly set the values. Using genetic algorithms for this problem proved to work exceptionally well when given enough time to train the network. The proposed architecture is found to work well in optimizing hyperparameters in affine, convolutional and recurrent layers proving to be a good choice for conventional supervised learning tasks.
Reinforcement Learning based Dynamic Model Selection for Short-Term Load Forecasting
With the growing prevalence of smart grid technology, short-term load forecasting (STLF) becomes particularly important in power system operations. There is a large collection of methods developed for STLF, but selecting a suitable method under varying conditions is still challenging. This paper develops a novel reinforcement learning based dynamic model selection (DMS) method for STLF. A forecasting model pool is first built, including ten state-of-the-art machine learning based forecasting models. Then a Q-learning agent learns the optimal policy of selecting the best forecasting model for the next time step, based on the model performance. The optimal DMS policy is applied to select the best model at each time step with a moving window. Numerical simulations on two-year load and weather data show that the Q-learning algorithm converges fast, resulting in effective and efficient DMS. The developed STLF model with Q-learning based DMS improves the forecasting accuracy by approximately 50%, compared to the state-of-the-art machine learning based STLF models.
Deriving item features relevance from collaborative domain knowledge
An Item based recommender system works by computing a similarity between items, which can exploit past user interactions (collaborative filtering) or item features (content based filtering). Collaborative algorithms have been proven to achieve better recommendation quality then content based algorithms in a variety of scenarios, being more effective in modeling user behaviour. However, they can not be applied when items have no interactions at all, i.e. cold start items. Content based algorithms, which are applicable to cold start items, often require a lot of feature engineering in order to generate useful recommendations. This issue is specifically relevant as the content descriptors become large and heterogeneous. The focus of this paper is on how to use a collaborative models domain-specific knowledge to build a wrapper feature weighting method which embeds collaborative knowledge in a content based algorithm. We present a comparative study for different state of the art algorithms and present a more general model. This machine learning approach to feature weighting shows promising results and high flexibility.
Evolutionary Data Measures: Understanding the Difficulty of Text Classification Tasks
• Rethinking floating point for deep learning• Synchronized Multi-Load Balancer with Fault Tolerance in Cloud• Neural CRF transducers for sequence labeling• An Algorithm for Integer Least-squares with Equality, Sparsity and Rank Constraints• Improving Zero-Shot Translation of Low-Resource Languages• Communication Through Breath: Aerosol Transmission• A method to construct exponential families by representation theory• Query-based Logo Segmentation• Handwriting Recognition in Low-resource Scripts using Adversarial Learning• Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding• Texture Synthesis Guided Deep Hashing for Texture Image Retrieval• Dependency-dependent Bounds for Sums of Dependent Random Variables• DeepKey: Towards End-to-End Physical Key Replication From a Single Photograph• Infinite Swapping using IID Samples• Semantic Role Labeling for Knowledge Graph Extraction from Text• On curves intersecting at most once, II• Continuity of Utility Maximization under Weak Convergence• Why Extension-Based Proofs Fail• False Positive Reduction in Lung Computed Tomography Images using Convolutional Neural Networks• Domain Reduction for Monotonicity Testing: A $o(d)$ Tester for Boolean Functions on Hypergrids• Cross-Component Registration for Multivariate Functional Data with Application to Longitudinal Growth Curves• Improving FISTA: Faster, Smarter and Greedier• Hamilton-Jacobi equations for mean-field disordered systems• On Quasi-Isometry of Threshold-Based Sampling• QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks• Towards a Zero-One Law for Entrywise Low Rank Approximation• SSCNets: A Selective Sobel Convolution-based Technique to Enhance the Robustness of Deep Neural Networks against Security Attacks• FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning• Estimating the Signal Reconstruction Error from Threshold-Based Sampling Without Knowing the Original Signal• Assembly in populations of social networks• Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning• Intrinsic Universal Measurements of Non-linear Embeddings• $\mathcal{L}2$ State Estimation with Guaranteed Convergence Speed in the Presence of Sporadic Measurements• Practical Batch Bayesian Optimization for Less Expensive Functions• The one comparing narrative social network extraction techniques• Medical code prediction with multi-view convolution and description-regularized label-dependent attention• Monte Carlo Simulations on robustness of functional location estimator based on several functional depth• 100% Reliable Algorithm for Second-Harmonic-Generation Frequency-Resolved Optical Gating• RePair in Compressed Space and Time• Fast Face Image Synthesis with Minimal Training• Efficient Inference on Deep Neural Networks by Dynamic Representations and Decision Gates• Percolation on the product graph of a regular tree and a line does not satisfy the triangle condition at the uniqueness threshold• FairMod – Making Predictive Models Discrimination Aware• Contingency-Aware Exploration in Reinforcement Learning• Discrepancy in random hypergraph models• Underwater Fish Detection using Deep Learning for Water Power Applications• DSIC: Deep Learning based Self-Interference Cancellation for In-Band Full Duplex Wireless• Improving the $\frac{1}{3}-\frac{2}{3}$ Conjecture for Width Two Posets• Lifted Proximal Operator Machines• Large and moderate deviations for a $\mathbb{R}^d$-valued branching random walk with a random environment in time• Deep Multiple Description Coding by Learning Scalar Quantization• An Efficient Network for Predicting Time-Varying Distributions• Complex variables for fractional-order systems• SLAMBooster: An Application-aware Controller for Approximation in SLAM• User-Friendly Covariance Estimation for Heavy-Tailed Distributions• Unsupervised RGBD Video Object Segmentation Using GANs• Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information• Workload-aware Automatic Parallelization for Multi-GPU DNN Training• Redefining Ultrasound Compounding: Computational Sonography• How to aggregate Top-lists: Score based approximation schemes• Cocktail BPSK: Energy Reused Scheme for High Achievable Data Rates• Characterization by observability inequalities of controllability and stabilization properties• PILAE: A Non-gradient Descent Learning Scheme for Deep Feedforward Neural Networks• StNet: Local and Global Spatial-Temporal Modeling for Action Recognition• Almost Optimal Distance Oracles for Planar Graphs• Combining Matrix Design for 2D DoA Estimation with Compressive Antenna Arrays using Stochastic Gradient Descent• Representation Learning by Reconstructing Neighborhoods• Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations• Parallel training of linear models without compromising convergence• You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization• WaveFlow – Towards Integration of Ultrasound Processing with Deep Learning• Robust optimization-based heuristic algorithm for the chance-constrained knapsack problem using submodularity• SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection• Low-Rank Phase Retrieval via Variational Bayesian Learning• Polyadic cyclic codes over a non-chain ring $\mathbb{F}{q}[u,v]/\langle f(u),g(v), uv-vu\rangle$• Supervised Linear Regression for Graph Learning from Graph Signals• Putting the Agents back in the Domain: A Two-Sorted Term-Modal Logic• Semi-Semantic Line-Cluster Assisted Monocular SLAM for Indoor Environments• Visualizing class specific heterogeneous tendencies in categorical data• On a generalization of iterated and randomized rounding• Log-Concave Polynomials III: Mason’s Ultra-Log-Concavity Conjecture for Independent Sets of Matroids• Continual Occlusions and Optical Flow Estimation• GPU-accelerated Simulation of Massive Spatial Data based on the Modified Planar Rotator Model• ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion• A Bayesian Semiparametric Jolly-Seber Model with Individual Heterogeneity: An Application to Migratory Mallards at Stopover• Real-time Driver Drowsiness Detection for Android Application Using Deep Neural Networks Techniques• When Do Envy-Free Allocations Exist?• Effective characterization for stochastic differential equations with tempered stable Lévy fluctuations• Identifying influential patents in citation networks using enhanced VoteRank centrality• A general lower bound for the domination number of cylindrical graphs• Leveraging Random Label Memorization for Unsupervised Pre-Training• Hardness of minimal symmetry breaking in distributed computing• Probabilistic Parameterized Polynomial Time• Power-law energy level-spacing distributions in fractals• Data Integration for Supporting Biomedical Knowledge Graph Creation at Large-Scale• Exact multiplicative updates for convolutional $β$-NMF in 2D• Matrix Completion With Variational Graph Autoencoders: Application in Hyperlocal Air Quality Inference• The equivalence of two tax processes• Composing Optimization Techniques for Vertex-Centric Graph Processing via Communication Channels• Fast and exact analysis for LRU caches• The distributed complexity of locally checkable problems on paths is decidable• Gradedness of the set of rook placements in $A_{n-1}$• Percolation of finite clusters and existence of infinite shielded paths• Biased landscapes for random Constraint Satisfaction Problems• Supply Chain Management analysis: a simulation approach of the Value Chain Operations Reference model (VCOR)• Matroid-minor Hopf algebra: a cancellation-free antipode formula and other applications of sign-reversing involutions• The External Interface for Extending WASP• Hodge-Riemann relations for Potts model partition functions• Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification• Combining Subgoal Graphs with Reinforcement Learning to Build a Rational Pathfinder• Role of Awareness and Universal Context in a Spiking Conscious Neural Network (SCNN): A New Perspective and Future Directions• ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks• Mixture of generalized linear models: identifiability and applications• Multi-armed Bandits with Compensation• On the complexity of cache analysis for different replacement policies• Learning Shared Dynamics with Meta-World Models• FUNN: Flexible Unsupervised Neural Network• Decoding Generic Visual Representations From Human Brain Activity using Machine Learning• A full-discrete exponential Euler approximation of invariant measure for parabolic stochastic partial differential equations• Kernel Conjugate Gradient Methods with Random Projections• A Network Reliability Approach to the Analysis of Combinatorial Repairable Threshold Schemes• A Biologically Plausible Learning Rule for Deep Learning in the Brain• Reliable Broadcast in Dynamic Networks with Locally Bounded Byzantine Failures• SCAV’18: Report of the 2nd International Workshop on Safe Control of Autonomous Vehicles• Non-ergodic Convergence Analysis of Heavy-Ball Algorithms• On the Evaluation of Common-Sense Reasoning in Natural Language Understanding• A human-editable Sign Language representation for software editing—and a writing system?• Conditions for the finiteness of the moments of the volume of level sets• Confidence Propagation through CNNs for Guided Sparse Depth Regression• Planting trees in graphs, and finding them back• Intervention Harvesting for Context-Dependent Examination-Bias Estimation• Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls• Log-Concave Polynomials II: High-Dimensional Walks and an FPRAS for Counting Bases of a Matroid• Statistical reform and the replication crisis• Verisig: verifying safety properties of hybrid systems with neural network controllers• Forecasting elections using compartmental models of infections• Prior Knowledge Helps Improve Beam Angle Optimization Efficiency in Radiotherapy Planning• Sonin’s argument, the shape of solitons, and the most stably singular matrix• TzK Flow – Conditional Generative Model• Optimal Control of Sweeping Processes in Robotics and Traffic Flow Models• Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control• Perturbations of supercritical oriented percolation and sticky Brownian webs• End-to-End Sound Source Separation Conditioned On Instrument Labels• Differences between Health Related News Articles from Reliable and Unreliable Media• Do RNNs learn human-like abstract word order preferences?• Learning Two Layer Rectified Neural Networks in Polynomial Time• Upper tail large deviations in Brownian directed percolation• Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs• Lower Bounds for Parallel and Randomized Convex Optimization• A note on antimagic orientations of even regular graphs• A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM• Fast Non-Bayesian Poisson Factorization for Implicit-Feedback Recommendations• Optimal Local Thresholds for Distributed Detection in Energy Harvesting Wireless Sensor Networks• Many-body localization in a quasiperiodic Fibonacci chain• Optimal Data Detection in Large MIMO• Global Attitude Stabilization using Pseudo-Targets• Multiscale entanglement clusters at the many-body localization phase transition
Like this:
Like Loading…
Related