What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence

THE well-known ancient Chinese philosopher Lao Tzu(老子)or Laozi(6th~4th century BC during the Spring and Autumn period)started his classic Tao Teh Ching《道德经》or Dao De Jing(see Fig.1)with six Chinese characters:"道(Dao)可(Ke)道(Dao)非(Fei)常(Chang)道(Dao)",which has been traditionally interpreted as“道可道,非常道”or"The Dao that can be spoken is not the eternal Dao".

Generative Adversarial Networks:Introduction and Outlook

Recently, generative adversarial networks(GANs)have become a research focus of artificial intelligence. Inspired by two-player zero-sum game, GANs comprise a generator and a discriminator, both trained under the adversarial learning idea.The goal of GANs is to estimate the potential distribution of real data samples and generate new samples from that distribution.Since their initiation, GANs have been widely studied due to their enormous prospect for applications, including image and vision computing, speech and language processing, etc. In this review paper, we summarize the state of the art of GANs and look into the future. Firstly, we survey GANs' proposal background,theoretic and implementation models, and application fields.Then, we discuss GANs' advantages and disadvantages, and their development trends. In particular, we investigate the relation between GANs and parallel intelligence,with the conclusion that GANs have a great potential in parallel systems research in terms of virtual-real interaction and integration. Clearly, GANs can provide substantial algorithmic support for parallel intelligence.

Parallel Learning:a Perspective and a Framework

The development of machine learning in complex system is hindered by two problems nowadays.The first problem is the inefficiency of exploration in state and action space,which leads to the data-hungry of some state-of-art data-driven algorithm.The second problem is the lack of a general theory which can be used to analyze and implement a complex learning system.In this paper,we proposed a general methods that can address both two issues.We combine the concepts of descriptive learning,predictive learning,and prescriptive learning into a uniform framework,so as to build a parallel system allowing learning system improved by self-boosting.Formulating a new perspective of data,knowledge and action,we provide a new methodology called parallel learning to design machine learning system for real-world problems.

Functional group differentiation of isomeric solvents enables distinct zinc anode chemistry

Electrolytes hold the key to realizing reliable zinc(Zn)anodes.Divergent organic molecules have been proven effective in stabilizing Zn anodes;however,irrational comparisons exist due to the uncontrolled molecular weights and functional group amounts.In this work,two“isomeric molecules”:1,2-dimethoxyethane(DME)and 1-methoxy-2-propanol(PM),with identical molecular weights but different functional groups,have been studied as co-solvents in electrolytes,which have delivered distinct electrochemical performance.Experimental and simulative study indicates the dipole moment induced by the hydroxyl groups in PM(higher molecular polarity than ether groups in DME)reconstructs the space charge region,enhances the concentration of Zn^(2+)in the vicinity of Zn anodes,and in-situ derives different solid electrolyte interphase(SEI)models and electrode-electrolyte interfaces,resulting in exceptional cycling stability.Remarkably,the Zn||Cu cell with PM worked over 2000 cycles with high Coulombic efficiency(CE)of 99.7%.The Zn||Zn symmetric cell cycled over 2000 h at 1 mA·cm^(−2),and showed excellent stability at an ultrahigh current density of 10 mA·cm^(−2)and capacity of 20 mAh·cm^(−2)over 200 h(depth of discharge,DOD of 70%).The Zn||sodium vanadate pouch cell with a high mass loading of 6.3 mg·cm^(−2)and a high capacity of 24 mAh demonstrates superior cyclability after 570 h.This work can be a good starting point to provide reliable guidance on electrolyte design for practical aqueous Zn batteries.

Image-based traffic signal control via world models

Traffic signal control is shifting from passive control to proactive control, which enables the controller to direct current traffic flow to reach its expected destinations. To this end, an effective prediction model is needed for signal controllers. What to predict, how to predict, and how to leverage the prediction for control policy optimization are critical problems for proactive traffic signal control. In this paper, we use an image that contains vehicle positions to describe intersection traffic states. Then, inspired by a model-based reinforcement learning method, DreamerV2,we introduce a novel learning-based traffic world model. The traffic world model that describes traffic dynamics in image form is used as an abstract alternative to the traffic environment to generate multi-step planning data for control policy optimization. In the execution phase, the optimized traffic controller directly outputs actions in real time based on abstract representations of traffic states, and the world model can also predict the impact of different control behaviors on future traffic conditions. Experimental results indicate that the traffic world model enables the optimized real-time control policy to outperform common baselines, and the model achieves accurate image-based prediction, showing promising applications in futuristic traffic signal control.