Variational Autoencoders (VAEs) provide a theoretically-backed framework for deep generative models. However, they often produce "blurry" images, which is linked to their training objective. Sampling in the most popular implementation, the Gaussian VAE, can be interpreted as simply injecting noise to the input of a deterministic decoder. In practice, this simply enforces a smooth latent space structure. We challenge the adoption of the full VAE framework on this specific point in favor of a simpler, deterministic one. Specifically, we investigate how substituting stochasticity with other explicit and implicit regularization schemes can lead to a meaningful latent space without having to force it to conform to an arbitrarily chosen prior. To retrieve a generative mechanism for sampling new data points, we propose to employ an efficient ex-post density estimation step that can be readily adopted both for the proposed deterministic autoencoders as well as to improve sample quality of existing VAEs. We show in a rigorous empirical study that regularized deterministic autoencoding achieves state-of-the-art sample quality on the common MNIST, CIFAR-10 and CelebA datasets.

In this paper, we develop a multi-agent reinforcement learning (MARL) framework to obtain online power control policies for a large energy harvesting (EH) multiple access channel, when only the causal information about the EH process and wireless channel is available. In the proposed framework, we model the online power control problem as a discrete-time mean-field game (MFG), and leverage the deep reinforcement learning technique to learn the stationary solution of the game in a distributed fashion. We analytically show that the proposed procedure converges to the unique stationary solution of the MFG. Using the proposed framework, the power control policies are learned in a completely distributed fashion. In order to benchmark the performance of the distributed policies, we also develop a deep neural network (DNN) based centralized as well as distributed online power control schemes. Our simulation results show the efficacy of the proposed power control policies. In particular, the DNN based centralized power control policies provide a very good performance for large EH networks for which the design of optimal policies is intractable using the conventional methods such as Markov decision processes. Further, performance of both the distributed policies is close to the throughput achieved by the centralized policies. The work in this paper will appear in part at IEEE ICASSP 2019 [1] and IEEE WiOpt 2019 [2]. This research has been partly supported by the ERC-PoC 727682 CacheMire project. I. INTRODUCTION Internet-of-things (IoT) [3] networks connect a large number of low power sensors whose lifespan is typically limited by the energy that can be stored in their batteries. In this context, the advent of the energy harvesting (EH) technology [4] promises to prolong the lifespan of IoT networks by enabling the nodes to operate by harvesting energy from environmental sources, e.g., the sun, the wind, etc.

Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment. Combined with the rule-based constraints, a Deep Q-Network (DQN) based method is applied for autonomous driving lane change decision-making task in this study. Through the combination of high-level lateral decision-making and low-level rule-based trajectory modification, a safe and efficient lane change behavior can be achieved. With the setting of our state representation and reward function, the trained agent is able to take appropriate actions in a real-world-like simulator. The generated policy is evaluated on the simulator for 10 times, and the results demonstrate that the proposed rule-based DQN method outperforms the rule-based approach and the DQN method.

I used to train my model on my local machine, where the memory is only sufficient for 10 examples per batch. However, when I migrated my model to AWS and used a bigger GPU (Tesla K80), I could accomodate a batch size of 32. However, the AWS models all performed very, very poorly with a large indication of overfitting. The model I am currently using is the inception-resnet-v2 model, and the problem I'm targeting is a computer vision one. One explanation I can think of is that it is probably the batch-norm process that makes it more used to the batch images.

Industry Research is an upscale platform to help key personnel in the business world in strategizing and taking visionary decisions based on facts and figures derived from in depth market research. We are one of the top report resellers in the market, dedicated towards bringing you an ingenious concoction of data parameters.

On February the 14th 2019 Open AI posted their peculiar love-letter to the AI community. They shared a 21-minute long blog talking about their new language model named GPT-2, examples of the text it had generated, and a slight warning. The blog ends with a series of possible policy implications and a release strategy. While we have grown accustomed to OpenAI sharing their full code bases alongside announcements, OpenAI is committed to making AI safe. On this occasion, releasing the full code was deemed unsafe, citing concerns around impersonation, misleading news, fake content, and spam/phishing attacks.

Optimal auction design is one of the cornerstones of economic theory. It is of great practical importance, as auctions are used across industries and by the public sector to organize the sale of their products and services. Concrete examples are the US FCC Incentive Auction, the sponsored search auctions conducted by web search engines such as Google, or the auctions run on platforms such as eBay. In the standard independent private valuations model, each bidder has a valuation function over subsets of items, drawn independently from not necessarily identical distributions. It is assumed that the auctioneer knows the distributions and can (and will) use this information in designing the auction. A major difficulty in designing auctions is that valuations are private and bidders need to be incentivized to report their valuations truthfully. The goal is to learn an incentive compatible auction that maximizes revenue. We would like to thank Yang Cai, Vincent Conitzer, Yannai Gonczarowski, Constantinos Daskalakis, Glenn Ellison, Sergiu Hart, Ron Lavi, Kevin Leyton-Brown, Shengwu Li, Noam Nisan, Parag Pathak, Alexander Rush, Karl Schlag, Alex Wolitzky, participants in the Economics and Computation Reunion Workshop at the Simons Institute, the NIPS'17 Workshop on Learning in the Presence of Strategic Behavior, a Dagstuhl Workshop on Computational Learning Theory meets Game Theory, the EC'18 Workshop on Algorithmic Game Theory and Data Science, the Annual Congress of the German Economic Association, participants in seminars at LSE, Technion, Hebrew, Google, HBS, MIT, and the anonymous reviewers on earlier versions of this paper for their helpful feedback. The first version of this paper was posted on arXiv on June 12, 2017.

The recent surge of text-based online counseling applications enables us to collect and analyze interactions between counselors and clients. A dataset of those interactions can be used to learn to automatically classify the client utterances into categories that help counselors in diagnosing client status and predicting counseling outcome. With proper anonymization, we collect counselor-client dialogues, define meaningful categories of client utterances with professional counselors, and develop a novel neural network model for classifying the client utterances. The central idea of our model, ConvMFiT, is a pre-trained conversation model which consists of a general language model built from an out-of-domain corpus and two role-specific language models built from unlabeled in-domain dialogues. The classification result shows that ConvMFiT outperforms state-of-the-art comparison models. Further, the attention weights in the learned model confirm that the model finds expected linguistic patterns for each category.

Deep learning has been successfully used in numerous applications because of its outstanding performance and the ability to avoid manual feature engineering. One such application is electroencephalogram (EEG) based brain-computer interface (BCI), where multiple convolutional neural network (CNN) models have been proposed for EEG classification. However, it has been found that deep learning models can be easily fooled with adversarial examples, which are normal examples with small deliberate perturbations. This paper proposes an unsupervised fast gradient sign method (UFGSM) to attack three popular CNN classifiers in BCIs, and demonstrates its effectiveness. We also verify the transferability of adversarial examples in BCIs, which means we can perform attacks even without knowing the architecture and parameters of the target models, or the datasets they were trained on. To our knowledge, this is the first study on the vulnerability of CNN classifiers in EEG-based BCIs, and hopefully will trigger more attention on the security of BCI systems.

In this work, we analyze the suitability of deep neural networks (DNNs) for the numerical solution of parametric problems. Such problems connect a parameter space with a solution state space via a so-called parametric map, [53]. One special case of such a parametric problem arises when the parametric map results from solving a partial differential equation (PDE) and the parameters describe physical or geometrical constraints of the PDE such as, for example, the shape of the physical domain, boundary conditions, or a source term. Applications that lead to these problems include modeling unsteady and steady heat and mass transfer, acoustics, fluid mechanics, or electromagnetics, [34]. Solving a parametric PDE for every point in the parameter space of interest individually typically leads to two types of problems.