Recursive Bayesian Pruning (RBP)
Recently, compression and acceleration of deep neural networks are in critic need. Bayesian generalization of structured pruning represents an important research direction to solve the above problem. However, the existing Bayesian methods ignore the dependency among neurons and filters for computational simplicity. In this study, we explore, under Bayesian framework, a structured pruning method with layer-wise sequential dependency assumed, a more general learning setting. Based on the property of Dirac distribution, we further derive a new dropout noise, which makes it possible to approximate the posterior of dropout noise knowing that of the previous layer. With the Dirac-like dropout noise, we further propose a recursive strategy, named \emph{Recursive Bayesian Pruning} (RBP), to train and prune networks in a layer-by-layer fashion. The unimportant neurons and filters are directly targeted and removed, taking the influence from the previous layer. Experiments on typical neural networks LeNet-300-100, LeNet-5 and VGG-16 have demonstrated the proposed method are competitive with or even outperform the state-of-the-art methods in several compression and acceleration metrics. …

Cascade Clustering and Reference Point Incremental Learning Based Interactive Algorithm (CLIA)
Researches have shown difficulties in obtaining proximity while maintaining diversity for solving many-objective optimization problems (MaOPs). The complexities of the true Pareto Front (PF) also pose serious challenges for the pervasive algorithms for their insufficient ability to adapt to the characteristics of the true PF with no priori. This paper proposes a cascade Clustering and reference point incremental Learning based Interactive Algorithm (CLIA) for many-objective optimization. In the cascade clustering process, using reference lines provided by the learning process, individuals are clustered and intraclassly sorted in a bi-level cascade style for better proximity and diversity. In the reference point incremental learning process, using the feedbacks from the clustering process, the proper generation of reference points is gradually obtained by incremental learning and the reference lines are accordingly repositioned. The advantages of the proposed interactive algorithm CLIA lie not only in the proximity obtainment and diversity maintenance but also in the versatility for the diverse PFs which uses only the interactions between the two processes without incurring extra evaluations. The experimental studies on the CEC’2018 MaOP benchmark functions have shown that the proposed algorithm CLIA has satisfactory covering of the true PFs, and is competitive, stable and efficient compared with the state-of-the-art algorithms. …

Conditional Progressive Growing of GAN (CPGGAN)
Accurate computer-assisted diagnosis can alleviate the risk of overlooking the diagnosis in a clinical environment. Towards this, as a Data Augmentation (DA) technique, Generative Adversarial Networks (GANs) can synthesize additional training data to handle small/fragmented medical images from various scanners; those images are realistic but completely different from the original ones, filling the data lack in the real image distribution. However, we cannot easily use them to locate the position of disease areas, considering expert physicians’ annotation as time-expensive tasks. Therefore, this paper proposes Conditional Progressive Growing of GANs (CPGGANs), incorporating bounding box conditions into PGGANs to place brain metastases at desired position/size on 256 x 256 Magnetic Resonance (MR) images, for Convolutional Neural Network-based tumor detection; this first GAN-based medical DA using automatic bounding box annotation improves the robustness during training. The results show that CPGGAN-based DA can boost 10% sensitivity in diagnosis with an acceptable amount of additional False Positives—even with physicians’ highly-rough and inconsistent bounding box annotation. Surprisingly, further realistic tumor appearance, achieved with additional normal brain MR images for CPGGAN training, does not contribute to detection performance, while even three expert physicians cannot accurately distinguish them from the real ones in Visual Turing Test. …

Bayes-ToMoP
Multiagent algorithms often aim to accurately predict the behaviors of other agents and find a best response during interactions accordingly. Previous works usually assume an opponent uses a stationary strategy or randomly switches among several stationary ones. However, in practice, an opponent may exhibit more sophisticated behaviors by adopting more advanced strategies, e.g., using a bayesian reasoning strategy. This paper presents a novel algorithm called Bayes-ToMoP which can efficiently detect and handle opponents using either stationary or higher-level reasoning strategies. Bayes-ToMoP also supports the detection of previous unseen policies and learning a best response policy accordingly. Deep Bayes-ToMoP is proposed by extending Bayes-ToMoP with DRL techniques. Experimental results show both Bayes-ToMoP and deep Bayes-ToMoP outperform the state-of-the-art approaches when faced with different types of opponents in two-agent competitive games. …