Topic Tag: bot

home Forums Topic Tag: bot

 The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations through Sexual Evolutionary Synthesis

  

Evolutionary deep intelligence was recently proposed as a method for achieving highly efficient deep neural network architectures over successive generations. Drawing inspiration from nature, we propose the incorporation of sexual evolutionary synthesis. Rather than the current asexual synthesis of…


 CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training

 

We propose an adversarial training procedure for learning a causal implicit generative model for a given causal graph. We show that adversarial training can be used to learn a generative model with true observational and interventional distributions if the generator architecture is consistent with …


 On Fairness and Calibration

The machine learning community has become increasingly concerned with the potential for bias and discrimination in predictive models, and this has motivated a growing line of work on what it means for a classification procedure to be “fair.” In particular, we investigate the tension bet…


 The Opacity of Backbones and Backdoors Under a Weak Assumption

Backdoors and backbones of Boolean formulas are hidden structural properties that are relevant to the analysis of the hardness of instances of the satisfiability problem, SAT. The development and analysis of algorithms to find and make use of these properties is thus useful to improve the performan…


 Artificial Intelligence and Data Science in the Automotive Industry

Data science and machine learning are the key technologies when it comes to the processes and products with automatic learning and optimization to be used in the automotive industry of the future. This article defines the terms “data science” (also referred to as “data analytics&#…


 Energy saving for building heating via a simple and efficient model-free control design: First steps with computer simulations

The model-based control of building heating systems for energy saving encounters severe physical, mathematical and calibration difficulties in the numerous attempts that has been published until now. This topic is addressed here via a new model-free control setting, where the need of any mathematic…


 A Quasi-isometric Embedding Algorithm

The Whitney embedding theorem gives an upper bound on the smallest embedding dimension of a manifold. If a data set lies on a manifold, a random projection into this reduced dimension will retain the manifold structure. Here we present an algorithm to find a projection that distorts the data as lit…


 Source localization in an ocean waveguide using supervised machine learning

 

Source localization in ocean acoustics is posed as a machine learning problem in which data-driven methods learn source ranges directly from observed acoustic data. The pressure received by a vertical linear array is preprocessed by constructing a normalized sample covariance matrix (SCM) and used …


 Implicit Regularization in Deep Learning

In an attempt to better understand generalization in deep learning, we study several possible explanations. We show that implicit regularization induced by the optimization method is playing a key role in generalization and success of deep learning models. Motivated by this view, we study how diffe…


 An Influence-Receptivity Model for Topic based Information Cascades

We consider the problem of estimating the latent structure of a social network based on observational data on information diffusion processes, or {it cascades}. Here for a given cascade, we only observe the time a node/agent is infected but not the source of infection. Existing literature has focus…


 An Efficient Method for Robust Projection Matrix Design

Our objective is to efficiently design a robust projection matrix $Phi$ for the Compressive Sensing (CS) systems when applied to the signals that are not exactly sparse. The optimal projection matrix is obtained by mainly minimizing the average coherence of the equivalent dictionary. In order to dr…


 Towards Neural Machine Translation with Latent Tree Attention

   

Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translation, pairing a recurrent neural network grammar encoder with a novel attentional…


 A multi-agent reinforcement learning model of common-pool resource appropriation

  

Humanity faces numerous problems of common-pool resource appropriation. This class of multi-agent social dilemma includes the problems of ensuring sustainable use of fresh water, common fisheries, grazing pastures, and irrigation systems. Abstract models of common-pool resource appropriation based …


 Measuring the Similarity of Sentential Arguments in Dialog

When people converse about social or political topics, similar arguments are often paraphrased by different speakers, across many different conversations. Debate websites produce curated summaries of arguments on such topics; these summaries typically consist of lists of sentences that represent fr…


 Convolutional Gaussian Processes

  

We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images. The main contribution of our work is the construction of an inter-domain inducing point approximation that is well-tailored to the convolutional…


 Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe

We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback. In this problem, the objective is to minimize a global loss function of all the actions, not necessarily a cumulative loss. This framework allows us to study a very…


 Proving the Incompatibility of Efficiency and Strategyproofness via SMT Solving

Two important requirements when aggregating the preferences of multiple agents are that the outcome should be economically efficient and the aggregation mechanism should not be manipulable. In this paper, we provide a computer-aided proof of a sweeping impossibility using these two conditions for r…


 Clustering of Data with Missing Entries using Non-convex Fusion Penalties

The presence of missing entries in data often creates challenges for pattern recognition algorithms. Traditional algorithms for clustering data assume that all the feature values are known for every data point. We propose a method to cluster data in the presence of missing information. Unlike conve…


 Neural Networks Regularization Through Invariant Features Learning

 

Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification task when few training samples are available. We attempt to s…


 The low-rank hurdle model

A composite loss framework is proposed for low-rank modeling of data consisting of interesting and common values, such as excess zeros or missing values. The methodology is motivated by the generalized low-rank framework and the hurdle method which is commonly used to analyze zero-inflated counts. …


 Learning Multi-item Auctions with (or without) Samples

We provide algorithms that learn simple auctions whose revenue is approximately optimal in multi-item multi-bidder settings, for a wide range of valuations including unit-demand, additive, constrained additive, XOS, and subadditive. We obtain our learning results in two settings. The first is the c…


 Symmetric Variational Autoencoder and Connections to Adversarial Learning

A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback-Leibler divergence. It is demonstrated that learning of the resulting symmetric VAE (sVAE) has close connections to previously developed adversarial-learning methods. This relationship helps unify the previ…


 The Network Nullspace Property for Compressed Sensing of Big Data over Networks

We adapt the nullspace property of compressed sensing for sparse vectors to semi-supervised learning of labels for network-structured datasets. In particular, we derive a sufficient condition, which we term the network nullspace property, for convex optimization methods to accurately learn labels w…


 Phylogenetic Convolutional Neural Networks in Metagenomics

    

Background: Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data ba…


 A Comparison on Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging

 

Deep neural networks (DNN) have been successfully applied for music classification tasks including music tagging. In this paper, we investigate the effect of audio preprocessing on music tagging with neural networks. We perform comprehensive experiments involving audio preprocessing using different…