Panoramic video provides immersive and interactive experience by enabling humans to control the field of view (FoV) through head movement (HM). Thus, HM plays a key role in modeling human attention on panoramic video. This paper establishes a database collecting subjects' HM in panoramic video sequences. From this database, we find that the HM data are highly consistent across subjects. Furthermore, we find that deep reinforcement learning (DRL) can be applied to predict HM positions, via maximizing the reward of imitating human HM scanpaths through the agent's actions. Based on our findings, we propose a DRL-based HM prediction (DHP) approach with offline and online versions, called offline-DHP and online-DHP. In offline-DHP, multiple DRL workflows are run to determine potential HM positions at each panoramic frame. Then, a heat map of the potential HM positions, named the HM map, is generated as the output of offline-DHP. In online-DHP, the next HM position of one subject is estimated given the currently observed HM position, which is achieved by developing a DRL algorithm upon the learned offline-DHP model. Finally, the experiments validate that our approach is effective in both offline and online prediction of HM positions for panoramic video, and that the learned offline-DHP model can improve the performance of online-DHP.

In this paper, a hybrid deep neural network scheduler (HDNNS) is proposed to solve job-shop scheduling problems (JSSPs). In order to mine the state information of schedule processing, a job-shop scheduling problem is divided into several classification-based subproblems. And a deep learning framework is used for solving these subproblems. HDNNS applies the convolution two-dimensional transformation method (CTDT) to transform irregular scheduling information into regular features so that the convolution operation of deep learning can be introduced into dealing with JSSP. The simulation experiments designed for testing HDNNS are in the context of JSSPs with different scales of machines and jobs as well as different time distributions for processing procedures. The results show that the MAKESPAN index of HDNNS is 9% better than that of HNN and the index is also 4% better than that of ANN in ZLP dataset. With the same neural network structure, the training time of the HDNNS method is obviously shorter than that of the DEEPRM method. In addition, the scheduler has an excellent generalization performance, which can address large-scale scheduling problems with only small-scale training data.

We first study the transmission property of red light in water in terms of extinction coefficient and channel bandwidth via Monte Carlo simulation, with an interesting finding that red light outperforms blue-green light in highly turbid water. We further propose and experimentally demonstrate a broadband underwater wireless optical communication system based on a simple and cost-effective TO56 red-light laser diode. We demonstrate a 1.324-Gb/s transmission at a bit error rate (BER) of 2.02 × 10^-3 over a 6-m underwater channel, by using 128-QAM OFDM signals and a low-cost 150-MHz positive-intrinsic-negative photodetector, with a record spectral efficiency higher than 7.32 bits/Hz. By using an avalanche photodetector and 32-QAM OFDM signals, we have achieved a record bit rate of 4.883 Gb/s at a BER of 3.20 × 10^-3 over a 6-m underwater channel.

Deep learning has redefined AI thanks to the rise of artificial neural networks, which are inspired by neurological networks in the brain. Through the years, this dualism between AI and neuroscience has brought immense benefits to both fields, allowing neural networks to be used in a plethora of applications. Neural networks use an efficient implementation of reverse differentiation, called backpropagation (BP). This algorithm, however, is often criticized for its biological implausibility (e.g., lack of local update rules for the parameters). Therefore, biologically plausible learning methods that rely on predictive coding (PC), a framework for describing information processing in the brain, are increasingly studied. Recent works prove that these methods can approximate BP up to a certain margin on multilayer perceptrons (MLPs), and asymptotically on any other complex model, and that zero-divergence inference learning (Z-IL), a variant of PC, is able to exactly implement BP on MLPs. However, the recent literature shows also that there is no biologically plausible method yet that can exactly replicate the weight update of BP on complex models. To fill this gap, in this paper, we generalize (PC and) Z-IL by directly defining it on computational graphs, and show that it can perform exact reverse differentiation. What results is the first PC (and so biologically plausible) algorithm that is equivalent to BP in the way of updating parameters on any neural network, providing a bridge between the interdisciplinary research of neuroscience and deep learning. Furthermore, the above results in particular also immediately provide a novel local and parallel implementation of BP.