The Weak Completion Semantics is a novel cognitive theory which has been successfully applied to the suppression task, the selection task, syllogistic reasoning, the belief bias effect, spatial reasoning as well as reasoning with conditionals. It is based on logic programming with skeptical abduction. Each program admits a least model under the three-valued Lukasiewicz logic, which can be computed as the least fixed point of an appropriate semantic operator. The semantic operator can be represented by a three-layer feed-forward network using the core method. Its least fixed point is the unique stable state of a recursive network which is obtained from the three-layer feed-forward core by mapping the activation of the output layer back to the input layer. The recursive network is embedded into a novel network to compute skeptical abduction. This paper presents a fully connectionist realization of the Weak Completion Semantics.

Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few years, deep learning has advanced radically in such a way that it can surpass human-level performance on a number of tasks. As a consequence, deep learning is being extensively used in most of the recent day-to-day applications. However, security of deep learning systems are vulnerable to crafted adversarial examples, which may be imperceptible to the human eye, but can lead the model to misclassify the output. In recent times, different types of adversaries based on their threat model leverage these vulnerabilities to compromise a deep learning system where adversaries have high incentives. Hence, it is extremely important to provide robustness to deep learning algorithms against these adversaries. However, there are only a few strong countermeasures which can be used in all types of attack scenarios to design a robust deep learning system. In this paper, we attempt to provide a detailed discussion on different types of adversarial attacks with various threat models and also elaborate the efficiency and challenges of recent countermeasures against them.

Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. These limitations make RNNs difficult to embed on mobile devices requiring real-time processes with limited hardware resources. To address the above issues, we introduce a method that can learn binary and ternary weights during the training phase to facilitate hardware implementations of RNNs. As a result, using this approach replaces all multiply-accumulate operations by simple accumulations, bringing significant benefits to custom hardware in terms of silicon area and power consumption. On the software side, we evaluate the performance (in terms of accuracy) of our method using long short-term memories (LSTMs) on various sequential models including sequence classification and language modeling. We demonstrate that our method achieves competitive results on the aforementioned tasks while using binary/ternary weights during the runtime. On the hardware side, we present custom hardware for accelerating the recurrent computations of LSTMs with binary/ternary weights. Ultimately, we show that LSTMs with binary/ternary weights can achieve up to 12x memory saving and 10x inference speedup compared to the full-precision implementation on an ASIC platform.

It is challenging to train deep neural networks robustly on the industrial-level data, since labels of such data are heavily noisy, and their label generation processes are normally agnostic. To handle these issues, by using the memorization effects of deep neural networks, we may train deep neural networks on the whole dataset only the first few iterations. Then, we may employ early stopping or the small-loss trick to train them on selected instances. However, in such training procedures, deep neural networks inevitably memorize some noisy labels, which will degrade their generalization. In this paper, we propose a meta algorithm called Pumpout to overcome the problem of memorizing noisy labels. By using scaled stochastic gradient ascent, Pumpout actively squeezes out the negative effects of noisy labels from the training model, instead of passively forgetting these effects. We leverage Pumpout to upgrade two representative methods: MentorNet and Backward Correction. Empirical results on benchmark datasets demonstrate that Pumpout can significantly improve the robustness of representative methods.

The theory of belief functions is widely used for data from multiple sources. Different evidence combination rules have been proposed in this framework according to the properties of the sources to combine. However, most of these combination rules are not efficient when there are a large number of sources. This is due to either the complexity or the existence of an absorbing element such as the total conflict mass function for the conjunctive based rules when applied on unreliable evidence. In this paper, based on the assumption that the majority of sources are reliable, a combination rule for a large number of sources is proposed using a simple idea: the more common ideas the sources share, the more reliable these sources are supposed to be. This rule is adaptable for aggregating a large number of sources which may not all be reliable. It will keep the spirit of the conjunctive rule to reinforce the belief on the focal elements with which the sources are in agreement. The mass on the emptyset will be kept as an indicator of the conflict. The proposed rule, called LNS-CR (Conjunctive combinationRule for a Large Number of Sources), is evaluated on synthetic mass functions. The experimental results verify that the rule can be effectively used to combine a large number of mass functions and to elicit the major opinion.

Recent work has studied the reasons for the remarkable performance of deep neural networks in image classification. We examine batch normalization on the one hand and the dynamical systems view of residual networks on the other hand. Our goal is in understanding the notions of stability and smoothness of the inter-layer propagation of ResNets so as to explain when they contribute to significantly enhanced performance. We postulate that such stability is of importance for the trained ResNet to transfer.

Credal partitions in the framework of belief functions can give us a better understanding of the analyzed data set. In order to find credal community structure in graph data sets, in this paper, we propose a novel evidential community detection algorithm based on density peaks (EDPC). Two new metrics, the local density $\rho$ and the minimum dissimi-larity $\delta$, are first defined for each node in the graph. Then the nodes with both higher $\rho$ and $\delta$ values are identified as community centers. Finally, the remaing nodes are assigned with corresponding community labels through a simple two-step evidential label propagation strategy. The membership of each node is described in the form of basic belief assignments , which can well express the uncertainty included in the community structure of the graph. The experiments demonstrate the effectiveness of the proposed method on real-world networks.

Stunning new maps covering over 2,000 square kilometers of northern Guatemala have revealed the site of an ancient Maya mega-city hidden in the dense tropical forest. Researchers uncovered more than 61,000 ancient structures at the site using LiDAR technology, which relies on laser pulses to map out the topography. Evidence from the exhaustive survey supports earlier suspicions that upwards of 11 million people lived in the Maya Lowlands from the year 650 to 800 CE. Stunning new maps covering over 2,000 square kilometers of northern Guatemala have revealed the site of an ancient Maya megacity hidden in the dense tropical forest. The researchers have now published the results of what they say is the largest LiDAR survey to date, months after first revealing their remarkable discovery.

Toronto's tech boom – driven in part by artificial intelligence research at the University of Toronto – has prompted talk of a "Silicon Valley North." But those actually ensconced in the Bay Area instead paint a picture of a research-driven innovation hub that's collaborative, inclusive and uniquely Canadian. At this year's three-day Elevate technology "festival" in Toronto, Eric Schmidt, a Google board member and former CEO, lauded the way Canada's post-secondary sector is being used to power the country's innovation engine and said Canada should be home to "one or two" of the globally important companies that spring from the coming AI revolution. "You have strong universities and the government is actually small enough, and sane enough, to help universities," Schmidt told a packed auditorium at the Sony Centre for the Performing Arts minutes before former U.S. vice-president and climate change crusader Al Gore took the stage. He added that Canada also benefits from close ties between post-secondary institutions and industry players.

A former employee of Google has warned of the web giant's'disturbing' plans for a search engine in China which could help Beijing monitor its citizens online. Jack Poulson wrote in a letter to the US Senate's commerce committee that the proposed Dragonfly website was'tailored to the censorship and surveillance demands of the Chinese government'. In his letter he also claimed that discussion of the plans among Google employees had been'increasingly stifled'. Mr Poulson was a senior research scientist at Google until he resigned last month in protest at the Dragonfly proposals. A former employee of Google has warned of the web giant's'disturbing' plans for a search engine in China which could help Beijing monitor its citizens online While China is home to the world's largest number of internet users, a 2015 report by US think tank Freedom House found that the country had the most restrictive online use policies of 65 nations it studied, ranking below Iran and Syria.