Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallelization. In this paper, we introduce a simple yet effective RNN connection structure, the DilatedRNN, which simultaneously tackles all of these challenges. The proposed architecture is characterized by multi-resolution dilated recurrent skip connections and can be combined flexibly with diverse RNN cells. Moreover, the DilatedRNN reduces the number of parameters needed and enhances training efficiency significantly, while matching state-of-the-art performance (even with standard RNN cells) in tasks involving very long-term dependencies. To provide a theory-based quantification of the architecture's advantages, we introduce a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing measures. We rigorously prove the advantages of the DilatedRNN over other recurrent neural architectures. The code for our method is publicly available at https://github.com/code-terminator/DilatedRNN.

Synthesizing realistic profile faces is promising for more efficiently training deep pose-invariant models for large-scale unconstrained face recognition, by populating samples with extreme poses and avoiding tedious annotations. However, learning from synthetic faces may not achieve the desired performance due to the discrepancy between distributions of the synthetic and real face images. To narrow this gap, we propose a Dual-Agent Generative Adversarial Network (DA-GAN) model, which can improve the realism of a face simulator's output using unlabeled real faces, while preserving the identity information during the realism refinement. The dual agents are specifically designed for distinguishing real v.s. fake and identities simultaneously. In particular, we employ an off-the-shelf 3D face model as a simulator to generate profile face images with varying poses. DA-GAN leverages a fully convolutional network as the generator to generate high-resolution images and an auto-encoder as the discriminator with the dual agents. Besides the novel architecture, we make several key modifications to the standard GAN to preserve pose and texture, preserve identity and stabilize training process: (i) a pose perception loss; (ii) an identity perception loss; (iii) an adversarial loss with a boundary equilibrium regularization term. Experimental results show that DA-GAN not only presents compelling perceptual results but also significantly outperforms state-of-the-arts on the large-scale and challenging NIST IJB-A unconstrained face recognition benchmark. In addition, the proposed DA-GAN is also promising as a new approach for solving generic transfer learning problems more effectively.

We introduce a simple yet surprisingly powerful model to incorporate attention in action recognition and human object interaction tasks. Our proposed attention module can be trained with or without extra supervision, and gives a sizable boost in accuracy while keeping the network size and computational cost nearly the same. It leads to significant improvements over state of the art base architecture on three standard action recognition benchmarks across still images and videos, and establishes new state of the art on MPII dataset with 12.5% relative improvement. We also perform an extensive analysis of our attention module both empirically and analytically. In terms of the latter, we introduce a novel derivation of bottom-up and top-down attention as low-rank approximations of bilinear pooling methods (typically used for fine-grained classification). From this perspective, our attention formulation suggests a novel characterization of action recognition as a fine-grained recognition problem.

Effective and efficient mitigation of malware is a long-time endeavor in the information security community. The development of an anti-malware system that can counteract an unknown malware is a prolific activity that may benefit several sectors. We envision an intelligent anti-malware system that utilizes the power of deep learning (DL) models. Using such models would enable the detection of newly-released malware through mathematical generalization. That is, finding the relationship between a given malware $x$ and its corresponding malware family $y$, $f: x \mapsto y$. To accomplish this feat, we used the Malimg dataset (Nataraj et al., 2011) which consists of malware images that were processed from malware binaries, and then we trained the following DL models 1 to classify each malware family: CNN-SVM (Tang, 2013), GRU-SVM (Agarap, 2017), and MLP-SVM. Empirical evidence has shown that the GRU-SVM stands out among the DL models with a predictive accuracy of ~84.92%. This stands to reason for the mentioned model had the relatively most sophisticated architecture design among the presented models. The exploration of an even more optimal DL-SVM model is the next stage towards the engineering of an intelligent anti-malware system.

Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion-MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of features nevertheless able to give good performance.

We address the problem of latent truth discovery, LTD for short, where the goal is to discover the underlying true values of entity attributes in the presence of noisy, conflicting or incomplete information. Despite a multitude of algorithms to address the LTD problem that can be found in literature, only little is known about their overall performance with respect to effectiveness (in terms of truth discovery capabilities), efficiency and robustness. A practical LTD approach should satisfy all these characteristics so that it can be applied to heterogeneous datasets of varying quality and degrees of cleanliness. We propose a novel algorithm for LTD that satisfies the above requirements. The proposed model is based on Restricted Boltzmann Machines, thus coined LTD-RBM. In extensive experiments on various heterogeneous and publicly available datasets, LTD-RBM is superior to state-of-the-art LTD techniques in terms of an overall consideration of effectiveness, efficiency and robustness.

EyeEm's Head of R&D Appu Shaji explains how his team developed a deep learning technology that understands aesthetic taste and applies it to your photos. As a child I waited anxiously for the arrival of each new issue of National Geographic Magazine. The magazine had amazing stories from around the world, but it was the stunning photographs that really stood out to me. The colors, shadows and composition intrigued me, as well as a union of visual arrangement and storytelling. This childhood fascination with photographs sparked a curiosity to understand their behavior, nuances and semantics. Ultimately, this curiosity drove me to study computer vision, which has empowered me to develop systems for understanding images from a computational and scientific perspective.

An image is worth a thousand words. Images tell stories that naturally appeal to humans. For instance, you may click multiple image of your pet and choose the one in which it's striking a pose rather than one which has no blurs or noise. We don't always choose images for their technical clarity and there are many times we prefer one image over the other because of its artistic appeal. Well, what if an AI could predict which images you find attractive based on aesthetics rather than technicality?

In a previous blog post we have seen how to build Convolutional Neural Networks (CNN) in Tensorflow, by building various CNN architectures (like LeNet5, AlexNet, VGGNet-16) from scratch and training them on the MNIST, CIFAR-10 and Oxflower17 datasets. It starts to get interesting when you start thinking about the practical applications of CNN and other Deep Learning methods. If you have been following the latest technical developments you probably know that CNN's are used for face recognition, object detection, analysis of medical images, automatic inspection in manufacturing processes, natural language processing tasks, any many other applications. You could say that you're only limited by your imagination and creativity (and of course motivation, energy and time) to find practical applications for CNN's. Inspired by Kaggle's Sattelite Imagery Feature Detection challenge, I would like to find out how easy it is to detect features (roads in this particular case) in sattelite and aerial images.

Deep learning can automatically select the features For a simple machine learning, a human has to tell the algorithm which combination of features to consider Deep learning finds the relationships on its own No human involvement Artificial Intelligence Types 43. "Ultra Deep Learning" Machine has learned so much, it can not only derive the rules, but detect when the rules change: detect the change in paradigms. Combines the supervised, un-supervised types and rule based machine learning into a more intelligent system.