Adaptive neurons compute confidence in a decision network

Humans and many animals have the ability to assess the confidence of their decisions. However, little is known about the underlying neural substrate and mechanism. In this study we propose a computational model consisting of a group of ’confidence neurons’ with adaptation, which are able to assess the confidence of decisions by detecting the slope of ramping activities of decision neurons. The simulated activities of ’confidence neurons’ in our simple model capture the typical features of confidence observed in humans and animals experiments. Our results indicate that confidence could be online formed along with the decision formation, and the adaptation properties could be used to monitor the formation of confidence during the decision making.

A Bayesian Approach to Risk-Based Autonomy for a Robotic System Executing a Sequence of Independent Tasks

Enabling higher levels of autonomy requires an increased ability to identify and handle internal faults and unforeseen changes in the environment. This work presents an approach to improve this ability for a robotic system executing a series of independent tasks, such as inspection, sampling, or intervention, at different locations. A dynamic decision network (DDN) is used to infer the presence of internal faults and the state of the environment by fusing information over time. This knowledge is used to make risk-informed decisions enabling the system to proactively avoid failure and to minimize the consequence of faults. Past states are evaluated with new information to identify and counteract previous sub-optimal actions. A case study on an inspection drone tasked with contact-based ultrasound inspection is presented. The case study successfully demonstrates the proposed capabilities while minimizing time use and maximizing mission completion.

FNet: A Two-Stream Model for Detecting Adversarial Attacks against 5G-Based Deep Learning Services

With the extensive application of artificial intelligence technology in 5G and Beyond Fifth Generation (B5G) networks, it has become a common trend for artificial intelligence to integrate into modern communication networks. Deep learning is a subset of machine learning and has recently led to significant improvements in many fields. In particular, many 5G-based services use deep learning technology to provide better services. Although deep learning is powerful, it is still vulnerable when faced with 5G-based deep learning services. Because of the nonlinearity of deep learning algorithms, slight perturbation input by the attacker will result in big changes in the output. Although many researchers have proposed methods against adversarial attacks, these methods are not always effective against powerful attacks such as CW. In this paper, we propose a new two-stream network which includes RGB stream and spatial rich model (SRM) noise stream to discover the difference between adversarial examples and clean examples. The RGB stream uses raw data to capture subtle differences in adversarial samples. The SRM noise stream uses the SRM filters to get noise features. We regard the noise features as additional evidence for adversarial detection. Then, we adopt bilinear pooling to fuse the RGB features and the SRM features. Finally, the final features are input into the decision network to decide whether the image is adversarial or not. Experimental results show that our proposed method can accurately detect adversarial examples. Even with powerful attacks, we can still achieve a detection rate of 91.3%. Moreover, our method has good transferability to generalize to other adversaries.

Making design decisions under uncertainties: probabilistic reasoning and robust product design

Making design decisions is characterized by a high degree of uncertainty, especially in the early phase of the product development process, when little information is known, while the decisions made have an impact on the entire product life cycle. Therefore, the goal of complexity management is to reduce uncertainty in order to minimize or avoid the need for design changes in a late phase of product development or in the use phase. With our approach we model the uncertainties with probabilistic reasoning in a Bayesian decision network explicitly, as the uncertainties are directly attached to parts of the design artifact′s model. By modeling the incomplete information expressed by unobserved variables in the Bayesian network in terms of probabilities, as well as the variation of product properties or parameters, a conclusion about the robustness of the product can be made. The application example of a rotary valve from engineering design shows that the decision network can support the engineer in decision-making under uncertainty. Furthermore, a contribution to knowledge formalization in the development project is made.

A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN

Forest fires are serious disasters that affect countries all over the world. With the progress of image processing, numerous image-based surveillance systems for fires have been installed in forests. The rapid and accurate detection and grading of fire smoke can provide useful information, which helps humans to quickly control and reduce forest losses. Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection. However, the research of CNN-based region detection and grading of fire is extremely scarce due to a challenging task which locates and segments fire regions using image-level annotations instead of inaccessible pixel-level labels. This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN. The multi-task framework can simultaneously implement the early-stage alarm, region detection, classification, and grading of fire smoke. To provide an accurate segmentation on image-level, we propose the weakly supervised fine segmentation method, which consists of a segmentation network and a decision network. We aggregate image-level information, instead of expensive pixel-level labels, from all training images into the segmentation network, which simultaneously locates and segments fire smoke regions. To train the segmentation network using only image-level annotations, we propose a two-stage weakly supervised learning strategy, in which a novel weakly supervised loss is proposed to roughly detect the region of fire smoke, and a new region-refining segmentation algorithm is further used to accurately identify this region. The decision network incorporating a residual spatial attention module is utilized to predict the category of forest fire smoke. To reduce the complexity of the Faster R-CNN, we first introduced a knowledge distillation technique to compress the structure of this model. To grade forest fire smoke, we used a 3-input/1-output fuzzy system to evaluate the severity level. We evaluated the proposed approach using a developed fire smoke dataset, which included five different scenes varying by the fire smoke level. The proposed method exhibited competitive performance compared to state-of-the-art methods.

A decision network account of reasoning about other people's choices

The ability to predict and reason about other people's choices is fundamental to social interaction. We propose that people reason about other people's choices using mental models that are similar to decision networks. Decision networks are extensions of Bayesian networks that incorporate the idea that choices are made in order to achieve goals. In our first experiment, we explore how people predict the choices of others. Our remaining three experiments explore how people infer the goals and knowledge of others by observing the choices that they make. We show that decision networks account for our data better than alternative computational accounts that do not incorporate the notion of goal-directed choice or that do not rely on probabilistic inference.

Adaptive Neurons Compute Confidence In A Decision Network

Human and many animals can asses the confidence of their decisions. However, little has been known about the underlying neural substrate and mechanism. Here we proposed a computational model consisting of one group of ’confidence neurons’ with adaptation, which is able to asses the confidence of decision by detecting the slope of ramping activities of decision neurons. The simulated activities of ’confidence neurons’ in our simple model capture the typical features of confidence in human and animals experiments. Our results indicate that confidence could be online formed along with the decision formation and the adaptation properties could be used to monitor the decision confidence in artificial intelligence.

An intelligent decision-making method for anti-jamming communication based on deep reinforcement learning

In order to solve the problem of intelligent anti-jamming decision-making in battlefield communication, this paper designs an intelligent decision-making method for communication anti-jamming based on deep reinforcement learning. Introducing experience replay and dynamic epsilon mechanism based on PHC under the framework of DQN algorithm, a dynamic epsilon-DQN intelligent decision-making method is proposed. The algorithm can better select the value of epsilon according to the state of the decision network and improve the convergence speed and decision success rate. During the decision-making process, the jamming signals of all communication frequencies are detected, and the results are input into the decision-making algorithm as jamming discriminant information, so that we can effectively avoid being jammed under the condition of no prior jamming information. The experimental results show that the proposed method adapts to various communication models, has a fast decision-making speed, and the average success rate of the convergent algorithm can reach more than 95%, which has a great advantage over the existing decision-making methods.