Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider videos. Learning generative models of video is a much harder task, requiring a model to capture the temporal dynamics of a scene, in addition to the visual presentation of objects. Although recent attempts at formulating generative models of video have had some success, current progress is hampered by (1) the lack of qualitative metrics that consider visual quality, temporal coherence, and diversity of samples, and (2) the wide gap between purely synthetic video datasets and challenging real-world datasets in terms of complexity. To this extent we propose Fr\'echet Video Distance (FVD), a new metric for generative models of video based on FID, and StarCraft 2 Videos (SCV), a collection of progressively harder datasets that challenge the capabilities of the current iteration of generative models for video. We conduct a large-scale human study, which confirms that FVD correlates well with qualitative human judgment of generated videos, and provide initial benchmark results on SCV.

This paper applies state-of-the-art techniques in deep learning and computer vision to measure visual similarities between architectural designs by different architects. Using a dataset consisting of web scraped images and an original collection of images of architectural works, we first train a deep convolutional neural network (DCNN) model capable of achieving 73% accuracy in classifying works belonging to 34 different architects. Through examining the weights in the trained DCNN model, we are able to quantitatively measure the visual similarities between architects that are implicitly learned by our model. Using this measure, we cluster architects that are identified to be similar and compare our findings to conventional classification made by architectural historians and theorists. Our clustering of architectural designs remarkably corroborates conventional views in architectural history, and the learned architectural features also coheres with the traditional understanding of architectural designs.

X-Ray image enhancement, along with many other medical image processing applications, requires the segmentation of images into bone, soft tissue, and open beam regions. We apply a machine learning approach to this problem, presenting an end-to-end solution which results in robust and efficient inference. Since medical institutions frequently do not have the resources to process and label the large quantity of X-Ray images usually needed for neural network training, we design an end-to-end solution for small datasets, while achieving state-of-the-art results. Our implementation produces an overall accuracy of 92%, F1 score of 0.92, and an AUC of 0.98, surpassing classical image processing techniques, such as clustering and entropy based methods, while improving upon the output of existing neural networks used for segmentation in non-medical contexts. The code used for this project is available online.

The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently needed given that the amount of dialogue history and corresponding representations can play an important role in the overall performance of a conversational system. This paper studies the amount of history required by conversational agents for reliably predicting dialogue rewards. The task of dialogue reward prediction is chosen for investigating the effects of varying amounts of dialogue history and their impact on system performance. Experimental results using a dataset of 18K human-human dialogues report that lengthy dialogue histories of at least 10 sentences are preferred (25 sentences being the best in our experiments) over short ones, and that lengthy histories are useful for training dialogue reward predictors with strong positive correlations between target dialogue rewards and predicted ones.

StarCraft (SC) is one of the most popular and successful Real Time Strategy (RTS) games. In recent years, SC is also considered as a testbed for AI research, due to its enormous state space, hidden information, multi-agent collaboration and so on. Thanks to the annual AIIDE and CIG competitions, a growing number of bots are proposed and being continuously improved. However, a big gap still remains between the top bot and the professional human players. One vital reason is that current bots mainly rely on predefined rules to perform macro actions. These rules are not scalable and efficient enough to cope with the large but partially observed macro state space in SC. In this paper, we propose a DRL based framework to do macro action selection. Our framework combines the reinforcement learning approach Ape-X DQN with Long-Short-Term-Memory (LSTM) to improve the macro action selection in bot. We evaluate our bot, named as LastOrder, on the AIIDE 2017 StarCraft AI competition bots set. Our bot achieves overall 83% win-rate, outperforming 26 bots in total 28 entrants.

Semi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning. The majority of existing semi-supervised VAEs utilize a classifier to exploit label information, where the parameters of the classifier are introduced to the VAE. Given the limited labeled data, learning the parameters for the classifiers may not be an optimal solution for exploiting label information. Therefore, in this paper, we develop a novel approach for semi-supervised VAE without classifier. Specifically, we propose a new model called Semi-supervised Disentangled VAE (SDVAE), which encodes the input data into disentangled representation and non-interpretable representation, then the category information is directly utilized to regularize the disentangled representation via the equality constraint. To further enhance the feature learning ability of the proposed VAE, we incorporate reinforcement learning to relieve the lack of data. The dynamic framework is capable of dealing with both image and text data with its corresponding encoder and decoder networks. Extensive experiments on image and text datasets demonstrate the effectiveness of the proposed framework.

This post adresses the general problem of constructing a deep learning based recommender system. The particular architecture discribed in the paper is the one powering the new smart feed of the iki service, pushing your skills on daily basis -- to check its performance, please try product beta. If you feel familiar with the general idea of recommender systems, mainstream approaches and would like to go straight to the details of our solution, please skip first two sections of the paper. Recommender systems have changed the way we interact with lots of services. Instead of providing static data they bring interactive experience, an option to leave your feedback and to personalise the information you are given.

Recent advances in deep learning and artificial generative models promise to expand existing capabilities of animation tools even further. Norah AI, a revolutionary animation tool recently released by Absentia startup, moves animation and game design industry into the AI era. It enables quick creation of all game elements, including 3D models and animations, game geometry, story weaving, and texturing, all with the minimal human input. The first version of Norah AI features Auto Rig tool, human motion simulation and blending, and Motion Editor that cover a wide variety of user cases in 3D animation and game design.

My journey into Deep Learning In this post I'll share how I've been studying Deep Learning and using it to solve data science problems.

About four billion people in the world are without a physical address. The MIT Media Lab and Facebook are teaming up to create a solution that will use a machine learning algorithm to identify and assign addresses from satellite images. The system would provide a cheap and efficient alternative to conventional mapping methods. According to a paper published by the researchers earlier this month, the team trained a deep-learning algorithm to scan satellite images and identify pixels that contain roads. Another algorithm took those pixels and stitched them together into a network of roads which could then be analyzed and split into quadrants.