Recommender systems have recently attracted many researchers in the deep learning community. The state-of-the-art deep neural network models used in recommender systems are typically multilayer perceptron and deep Autoencoder (DAE), among which DAE usually shows better performance due to its superior capability to reconstruct the inputs. However, we found existing DAE recommendation systems that have similar implementations on similar datasets result in vastly different parameter settings. In this work, we have built a flexible DAE model, named FlexEncoder that uses configurable parameters and unique features to analyse the parameter influences on the prediction accuracy of recommender systems. This will help us identify the best-performance parameters given a dataset. Extensive evaluation on the MovieLens datasets are conducted, which drives our conclusions on the influences of DAE parameters. Specifically, we find that DAE parameters strongly affect the prediction accuracy of the recommender systems, and the effect is transferable to similar datasets in a larger size. We open our code to public which could benefit both new users for DAE -- they can quickly understand how DAE works for recommendation systems, and experienced DAE users -- it easier for them to tune the parameters on different datasets.

Multiple sclerosis (MS) is an inflammatory demyelinating disease of the central nervous system (CNS) that results in focal injury to the grey and white matter. The presence of white matter lesions biases morphometric analyses such as registration, individual longitudinal measurements and tissue segmentation for brain volume measurements. Lesion-inpainting with intensities derived from surround healthy tissue represent one approach to alleviate such problems. However, existing methods inpaint lesions based on texture information derived from local surrounding tissue, often leading to inconsistent inpainting and the generation of artifacts such as intensity discrepancy and blurriness. Based on these observations, we propose non-local partial convolutions (NLPC) which integrates a Unet-like network with the non-local module. The non-local module is exploited to capture long range dependencies between the lesion area and remaining normal-appearing brain regions. Then, the lesion area is filled by referring to normal-appearing regions with more similar features. This method generates inpainted regions that appear more realistic and natural. Our quantitative experimental results also demonstrate superiority of this technique of existing state-of-the-art inpainting methods.

Invariant and equivariant networks have been successfully used for learning images, sets, point clouds, and graphs. A basic challenge in developing such networks is finding the maximal collection of invariant and equivariant linear layers. Although this question is answered for the first three examples (for popular transformations, at-least), a full characterization of invariant and equivariant linear layers for graphs is not known. In this paper we provide a characterization of all permutation invariant and equivariant linear layers for (hyper-)graph data, and show that their dimension, in case of edge-value graph data, is 2 and 15, respectively. More generally, for graph data defined on k-tuples of nodes, the dimension is the k-th and 2k-th Bell numbers. Orthogonal bases for the layers are computed, including generalization to multi-graph data. The constant number of basis elements and their characteristics allow successfully applying the networks to different size graphs. From the theoretical point of view, our results generalize and unify recent advancement in equivariant deep learning. In particular, we show that our model is capable of approximating any message passing neural network Applying these new linear layers in a simple deep neural network framework is shown to achieve comparable results to state-of-the-art and to have better expressivity than previous invariant and equivariant bases.

Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that is inherently consistent through a period of time is in desire, especially for tasks with either sparse rewards or long term information. In this work, we introduce a novel on-policy temporally consistent exploration strategy - Neural Adaptive Dropout Policy Exploration (NADPEx) - for deep reinforcement learning agents. Modeled as a global random variable for conditional distribution, dropout is incorporated to reinforcement learning policies, equipping them with inherent temporal consistency, even when the reward signals are sparse. Two factors, gradients' alignment with the objective and KL constraint in policy space, are discussed to guarantee NADPEx policy's stable improvement. Our experiments demonstrate that NADPEx solves tasks with sparse reward while naive exploration and parameter noise fail. It yields as well or even faster convergence in the standard mujoco benchmark for continuous control.

This paper introduces a novel deep learning framework for image animation. Given an input image with a target object and a driving video sequence depicting a moving object, our framework generates a video in which the target object is animated according to the driving sequence. This is achieved through a deep architecture that decouples appearance and motion information. Our framework consists of three main modules: (i) a Keypoint Detector unsupervisely trained to extract object keypoints, (ii) a Dense Motion prediction network for generating dense heatmaps from sparse keypoints, in order to better encode motion information and (iii) a Motion Transfer Network, which uses the motion heatmaps and appearance information extracted from the input image to synthesize the output frames. We demonstrate the effectiveness of our method on several benchmark datasets, spanning a wide variety of object appearances, and show that our approach outperforms state-of-the-art image animation and video generation methods.

We recently published a series of articles looking at the top Python libraries, across Data science, Deep Learning and Machine Learning. As the year draws to a close, we thought we'd give you a special Christmas gift, and collate these into a KDnuggets official top Python libraries in 2018. As always, we want your opinions! So, if you think we've unfairly left any out, or if you disagree with any of our choices, please let us know in the comments section below. Shape size is proportional to number of commits.

The last few years have been a dream run for Artificial Intelligence enthusiasts and machine learning professionals. These technologies have evolved from being a niche to becoming mainstream, and are impacting millions of lives today. Countries now have dedicated AI ministers and budgets to make sure they stay relevant in this race. The same has been true for a data science professional. A few years back – you would have been comfortable knowing a few tools and techniques. There is so much happening in this domain and so much to keep pace with – it feels mind boggling at times. This is why I thought of taking a step back and looking at the developments in some of the key areas in Artificial Intelligence from a data science practitioners' perspective. What happened in 2018 and what can be expected in 2019? Read this article to find out!

The transitional rise of Artificial intelligence in the most recent decade has prodded a gigantic demand for AI and ML skills in the present market. ML-based innovation is currently utilized as a part of relatively every industry whether it be finance or say health care. In this article, we will be highlighting 5 tools and their respective frameworks that features on the'hot rundown' for Artificial Intelligence & Machine Learning Models. A short depiction alongside the features is provided for each tool or framework. Lets us travel and discover precisely, why the accompanying tools and frameworks are positioned so high.

Perhaps more important than their conclusions was the writing process that led to those conclusions -- on Github, in the open, similar in fashion to open source software development. Writing a review openly on Github reduces bias and takes advantage of the wisdom of crowds. On the right is a snapshot of an exchange between myself and one of the authors in which we decided not to comment on certain questions we had considered earlier. We do not discuss these questions in the review, but this exchange clarifies how we think about them -- and that is the added value of the open writing process. The review is available as a preprint on bioRxiv and the latest version is available on Github.

The hope is that deep learning solutions could be used to not just react to network breaches based on predetermined rules or understand breaches based on those witnessed before, but to identify breaches and respond to them much like a human would; outwitting its opponent irrespective of their skill, technique or creativity.