Compared with artificial neural networks (ANNs), spiking neural networks (SNNs) are promising to explore the brain-like behaviors since the spikes could encode more spatio-temporal information. Although pre-training from ANN or direct training based on backpropagation (BP) makes the supervised training of SNNs possible, these methods only exploit the networks' spatial domain information which leads to the performance bottleneck and requires many complicated training skills. Another fundamental issue is that the spike activity is naturally non-differentiable which causes great difficulties in training SNNs. To this end, we build an iterative LIF model that is more friendly for gradient descent training. By simultaneously considering the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD) in the training phase, as well as an approximated derivative for the spike activity, we propose a spatio-temporal backpropagation (STBP) training framework without using any complicated technology. We achieve the best performance of multi-layered perceptron (MLP) compared with existing state-of-the-art algorithms over the static MNIST and the dynamic N-MNIST dataset as well as a custom object detection dataset. This work provides a new perspective to explore the high-performance SNNs for future brain-like computing paradigm with rich spatio-temporal dynamics.

Instance- and label-dependent label noise (ILN) is widely existed in real-world datasets but has been rarely studied. In this paper, we focus on a particular case of ILN where the label noise rates, representing the probabilities that the true labels of examples flip into the corrupted labels, have upper bounds. We propose to handle this bounded instance- and label-dependent label noise under two different conditions. First, theoretically, we prove that when the marginal distributions $P(X|Y=+1)$ and $P(X|Y=-1)$ have non-overlapping supports, we can recover every noisy example's true label and perform supervised learning directly on the cleansed examples. Second, for the overlapping situation, we propose a novel approach to learn a well-performing classifier which needs only a few noisy examples to be labeled manually. Experimental results demonstrate that our method works well on both synthetic and real-world datasets.

Brain-Computer Interface (BCI) uses brain signals in order to provide a new method for communication between human and outside world. Feature extraction, selection and classification are among the main matters of concerns in signal processing stage of BCI. In this article, we present our findings about the most effective features and classifiers in some brain tasks. Six different groups of classical features and twelve classifiers have been examined in nine datasets of brain signal. The results indicate that energy of brain signals in {\alpha} and \b{eta} frequency bands, together with some statistical parameters are more effective, comparing to the other types of extracted features. In addition, Bayesian classifier with Gaussian distribution assumption and also Support Vector Machine (SVM) show to classify different BCI datasets more accurately than the other classifiers. We believe that the results can give an insight about a strategy for blind classification of brain signals in brain-computer interface.

In this paper we present a comprehensive view of prominent causal discovery algorithms, categorized into two main categories (1) assuming acyclic and no latent variables, and (2) allowing both cycles and latent variables, along with experimental results comparing them from three perspectives: (a) structural accuracy, (b) standard predictive accuracy, and (c) accuracy of counterfactual inference. For (b) and (c) we train causal Bayesian networks with structures as predicted by each causal discovery technique to carry out counterfactual or standard predictive inference. We compare causal algorithms on two pub- licly available and one simulated datasets having different sample sizes: small, medium and large. Experiments show that structural accuracy of a technique does not necessarily correlate with higher accuracy of inferencing tasks. Fur- ther, surveyed structure learning algorithms do not perform well in terms of structural accuracy in case of datasets having large number of variables.

Although it is recently introduced, in last few years, generative adversarial network (GAN) has been shown many promising results to generate realistic samples. However, it is hardly able to control generated samples since input variables for a generator are from a random distribution. Some attempts have been made to control generated samples from GAN, but they have not shown good performances with difficult problems. Furthermore, it is hardly possible to control the generator to concentrate on reality or distinctness. For example, with existing models, a generator for face image generation cannot be set to concentrate on one of the two objectives, i.e. generating realistic face and generating difference face according to input labels. Here, we propose controllable GAN (CGAN) in this paper. CGAN shows powerful performance to control generated samples; in addition, it can control the generator to concentrate on reality or distinctness. In this paper, CGAN is evaluated with CelebA datasets. We believe that CGAN can contribute to the research in generative neural network models.

A significant literature studies ways of employing prior knowledge to improve power and precision of multiple testing procedures. Some common forms of prior knowledge may include (a) a priori beliefs about which hypotheses are null, modeled by non-uniform prior weights; (b) differing importances of hypotheses, modeled by differing penalties for false discoveries; (c) multiple arbitrary partitions of the hypotheses into known (possibly overlapping) groups, indicating (dis)similarity of hypotheses; and (d) knowledge of independence, positive or arbitrary dependence between hypotheses or groups, allowing for more aggressive or conservative procedures. We present a unified algorithmic framework called p-filter for global null testing and false discovery rate (FDR) control that allows the scientist to incorporate all four types of prior knowledge (a)-(d) simultaneously, recovering a wide variety of common algorithms as special cases.

Cheaper, more capable, and more flexible technologies are accelerating the growth of fully automated production facilities. The key challenge for companies will be deciding how best to harness their power. At one Fanuc plant in Oshino, Japan, industrial robots produce industrial robots, supervised by a staff of only four workers per shift. In a Philips plant producing electric razors in the Netherlands, robots outnumber the nine production workers by more than 14 to 1. Camera maker Canon began phasing out human labor at several of its factories in 2013. This "lights out" production concept--where manufacturing activities and material flows are handled entirely automatically--is becoming an increasingly common attribute of modern manufacturing.

NoBroker.com is a customer to customer property marketplace that makes it free for home owners and tenants to list properties and find properties by removing the broker from the equation. Typically the amount paid by both the owners and the tenants or buyers towards brokerage adds very little value to either party. This was an unnecessary intermediation cost which NoBroker.com is removing and helping the customer save. The property portal has been around for three years, and has been designed to be simple to use. More than twenty six lakh customers have used the services offered by the portal.

A man uses his mobile phone near an Apple store logo in Beijing. The latest iPhone is expected to include facial recognition as an unlocking feature but do away with the home button. A man uses his mobile phone near an Apple store logo in Beijing. The latest iPhone is expected to include facial recognition as an unlocking feature but do away with the home button. Back in 2007, the hype around Apple's new phone was all about the keyboard -- or lack thereof.

India's logistics sector is booming, and is touted to be worth $307 billion by 2020. Retail, e-commerce and manufacturing have propelled its rapid growth, but so far it has been largely unorganized, mainly thanks to outdated processes and limited technological intervention. This technological gap has created multiple opportunities for startups to provide innovative solutions to mitigate the industry's connectivity problems, service e-commerce players better and provide a seamless customer experience. Shadowfax is one of India's first logistics startups planning to run a pilot project using a drone. Gurgaon-based hyperlocal logistics startup Shadowfax is one such startup.