Advances on bidirectional intelligence are overviewed along three threads,with extensions and new perspectives.The first thread is about bidirectional learning architecture,exploring five dualities that enable Lmser s...Advances on bidirectional intelligence are overviewed along three threads,with extensions and new perspectives.The first thread is about bidirectional learning architecture,exploring five dualities that enable Lmser six cognitive functions and provide new perspectives on which a lot of extensions and particularlly flexible Lmser are proposed.Interestingly,either or two of these dualities actually takes an important role in recent models such as U-net,ResNet,and Dense Net.The second thread is about bidirectional learning principles unified by best yIng-yAng(IA)harmony in BYY system.After getting insights on deep bidirectional learning from a bird-viewing on existing typical learning principles from one or both of the inward and outward directions,maximum likelihood,variational principle,and several other learning principles are summarised as exemplars of the BYY learning,with new perspectives on advanced topics.The third thread further proceeds to deep bidirectional intelligence,driven by long term dynamics(LTD)for parameter learning and short term dynamics(STD)for image thinking and rational thinking in harmony.Image thinking deals with information flow of continuously valued arrays and especially image sequence,as if thinking was displayed in the real world,exemplified by the flow from inward encoding/cognition to outward reconstruction/transformation performed in Lmser learning and BYY learning.In contrast,rational thinking handles symbolic strings or discretely valued vectors,performing uncertainty reasoning and problem solving.In particular,a general thesis is proposed for bidirectional intelligence,featured by BYY intelligence potential theory(BYY-IPT)and nine essential dualities in architecture,fundamentals,and implementation,respectively.Then,problems of combinatorial solving and uncertainty reasoning are investigated from this BYY IPT perspective.First,variants and extensions are suggested for AlphaGoZero like searching tasks,such as traveling salesman problem(TSP)and attributed graph matching(AGM)that are turned into Go like problems with help of a feature enrichment technique.Second,reasoning activities are summarized under guidance of BYY IPT from the aspects of constraint satisfaction,uncertainty propagation,and path or tree searching.Particularly,causal potential theory is proposed for discovering causal direction,with two roads developed for its implementation.展开更多
We discuss how recent advances in phase-recovery imaging techniques in combination with plasmonic UTSs （ultrathin condensers） with a semiconductor substrate have paved the way for the development of novel optical na...We discuss how recent advances in phase-recovery imaging techniques in combination with plasmonic UTSs （ultrathin condensers） with a semiconductor substrate have paved the way for the development of novel optical nanoscopes. These optical nanoscopes are capable of imaging the intensity and the phase of the electric field distribution at the sample＇s plane.展开更多
The number of constraints imposed on the sur- face, the light source, the camera model and in particular the initial information makes shape from shading （SFS） very dif- ficult for real applications. There are a con...The number of constraints imposed on the sur- face, the light source, the camera model and in particular the initial information makes shape from shading （SFS） very dif- ficult for real applications. There are a considerable number of approaches which require an initial data about the 3D ob- ject such as boundary conditions （BC）. However, it is difficult to obtain these information for each point of the object Edge in the image, thus the application of these approaches is lim- ited. This paper shows an improvement of the Global View method proposed by Zhu and Shi [1]. The main improvement is that we make the resolution done automatically without any additional information on the 3D object. The method in- volves four steps. The first step is to determine the singular curves and the relationship between them. In the second step, we generate the global graph, determine the sub-graphs, and determine the partial and global configuration. The proposed method to determine the convexity and the concavity of the singular curves is applied in the third step. Finally, we apply the Fast-Marching method to reconstruct the 3D object. Our approach is successfully tested on some synthetic and real im- ages. Also, the obtained results are compared and discussed with some previous methods.展开更多
基金supported by the Zhi-Yuan Chair Professorship Start-up Grant (WF220103010) from Shanghai Jiao Tong University
文摘Advances on bidirectional intelligence are overviewed along three threads,with extensions and new perspectives.The first thread is about bidirectional learning architecture,exploring five dualities that enable Lmser six cognitive functions and provide new perspectives on which a lot of extensions and particularlly flexible Lmser are proposed.Interestingly,either or two of these dualities actually takes an important role in recent models such as U-net,ResNet,and Dense Net.The second thread is about bidirectional learning principles unified by best yIng-yAng(IA)harmony in BYY system.After getting insights on deep bidirectional learning from a bird-viewing on existing typical learning principles from one or both of the inward and outward directions,maximum likelihood,variational principle,and several other learning principles are summarised as exemplars of the BYY learning,with new perspectives on advanced topics.The third thread further proceeds to deep bidirectional intelligence,driven by long term dynamics(LTD)for parameter learning and short term dynamics(STD)for image thinking and rational thinking in harmony.Image thinking deals with information flow of continuously valued arrays and especially image sequence,as if thinking was displayed in the real world,exemplified by the flow from inward encoding/cognition to outward reconstruction/transformation performed in Lmser learning and BYY learning.In contrast,rational thinking handles symbolic strings or discretely valued vectors,performing uncertainty reasoning and problem solving.In particular,a general thesis is proposed for bidirectional intelligence,featured by BYY intelligence potential theory(BYY-IPT)and nine essential dualities in architecture,fundamentals,and implementation,respectively.Then,problems of combinatorial solving and uncertainty reasoning are investigated from this BYY IPT perspective.First,variants and extensions are suggested for AlphaGoZero like searching tasks,such as traveling salesman problem(TSP)and attributed graph matching(AGM)that are turned into Go like problems with help of a feature enrichment technique.Second,reasoning activities are summarized under guidance of BYY IPT from the aspects of constraint satisfaction,uncertainty propagation,and path or tree searching.Particularly,causal potential theory is proposed for discovering causal direction,with two roads developed for its implementation.
文摘We discuss how recent advances in phase-recovery imaging techniques in combination with plasmonic UTSs （ultrathin condensers） with a semiconductor substrate have paved the way for the development of novel optical nanoscopes. These optical nanoscopes are capable of imaging the intensity and the phase of the electric field distribution at the sample＇s plane.
文摘The number of constraints imposed on the sur- face, the light source, the camera model and in particular the initial information makes shape from shading （SFS） very dif- ficult for real applications. There are a considerable number of approaches which require an initial data about the 3D ob- ject such as boundary conditions （BC）. However, it is difficult to obtain these information for each point of the object Edge in the image, thus the application of these approaches is lim- ited. This paper shows an improvement of the Global View method proposed by Zhu and Shi [1]. The main improvement is that we make the resolution done automatically without any additional information on the 3D object. The method in- volves four steps. The first step is to determine the singular curves and the relationship between them. In the second step, we generate the global graph, determine the sub-graphs, and determine the partial and global configuration. The proposed method to determine the convexity and the concavity of the singular curves is applied in the third step. Finally, we apply the Fast-Marching method to reconstruct the 3D object. Our approach is successfully tested on some synthetic and real im- ages. Also, the obtained results are compared and discussed with some previous methods.
