Motor imagery electroencephalography (MI-EEG), which is an important subfield of active brain–computer interface (BCI) systems, can be applied to help disabled people to consciously and directly control prosthesis or external devices, aiding them in certain daily activities. However, the low signal-to-noise ratio and spatial resolution make MI-EEG decoding a challenging task. Recently, some deep neural approaches have shown good improvements over state-of-the-art BCI methods. In this study, an end-to-end scheme that includes a multi-layer convolution neural network is constructed for an accurate spatial representation of multi-channel grouped MI-EEG signals, which is employed to extract the useful information present in a multi-channel MI signal. Then the invariant spatial representations are captured from across-subjects training for enhancing the generalization capability through a stacked sparse autoencoder framework, which is inspired by representative deep learning models. Furthermore, a quantitative experimental analysis is conducted on our private dataset and on a public BCI competition dataset. The results show the effectiveness and significance of the proposed methodology.

/pdf/a-novel-deep-learning-scheme-for-motor-imagery-eeg-decoding-2fnclx7fke.pdf

A Novel Deep Learning Scheme for Motor Imagery EEG Decoding Based on Spatial Representation Fusion

In Computer vision systems, computer vision works by imitating humans in their vision way which is known as the human vision system (HVS). In HVS, humans use their eyes and brains in order to see and classify any object around them. Hence, computer vision systems imitate HSV by developing several algorithms for classifying images and objects. The main goal of this paper is to propose a model for identifying and classifying the Arabic handwritten digits with high accuracy.  The concept of deep learning via the convolutional neural network (CNN) with the ADBase database is used to achieve the goal. The training is done by having a 3*3 and 5*5 filters. Basically, while the classification phase distinct learning rates are used to train the network. The obtained results are encouraging and promising.

https://www.ijcnis.org/index.php/ijcnis/article/download/4807/428

Handwritten Arabic Digit Recognition Using Convolutional Neural Network

Despite its remarkable empirical success as a highly competitive branch of artificial intelligence, deep learning is often blamed for its widely known low interpretation and lack of firm and rigorous mathematical foundation. However, most theoretical endeavor is devoted in discriminative deep learning case, whose complementary part is generative deep learning. To the best of our knowledge, we firstly highlight landscape of empirical error in generative case to complete the full picture through exquisite design of image super resolution under norm based capacity control. Our theoretical advance in interpretation of the training dynamic is achieved from both mathematical and biological sides.

Theory of Generative Deep Learning : Probe Landscape of Empirical Error via Norm Based Capacity Control

Evolution of deep learning shows that some algorithmic tricks are more durable, while others are not. To the best of our knowledge, we firstly summarize 5 more durable and complete deep learning components for vision, that is, WARSHIP. Moreover, we give a biological overview of WARSHIP, emphasizing brain-inspired computing of WARSHIP. As a step towards WARSHIP, our case study of image super resolution combines 3 components of RSH to deploy a CNN model of WARSHIP-XZNet, which performs a happy medium between speed and performance.

Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution

Single-objective to multi-objective/many-objective optimization (SMO) is a new paradigm in the evolutionary transfer optimization (ETO), since there are only “1 + 4” pioneering works on SMOs so far, that is, “1” is continuous and is firstly performed by Professors L. Feng and H.D. Wang, and “4” are firstly proposed by our group for discrete cases. As a new computational paradigm, theoretical insights into SMOs are relatively rare now. Therefore, we present a proposal on the fine brushworks of SMOs for theoretical advances here, which is based on a case study of a permutation flow shop scheduling problem (PFSP) in manufacturing systems via lenses of building blocks, transferring gaps, auxiliary task and asynchronous rhythms. The empirical studies on well-studied benchmarks enrich the rough strokes of SMOs and guide future designs and practices in ETO based manufacturing scheduling, and even ETO based evolutionary processes for engineering optimization in other cases.

/pdf/evolutionary-process-for-engineering-optimization-in-vwhwo9ss.pdf

Evolutionary Process for Engineering Optimization in Manufacturing Applications: Fine Brushworks of Single-Objective to Multi-Objective/Many-Objective Optimization

Theory of Generative Deep Learning II:Probe Landscape of Empirical Error via Norm Based Capacity Control

Evolution of deep learning shows that some algorithmic tricks are more durable , while others are not. To the best of our knowledge, we firstly summarize 5 more durable and complete deep learning components for vision, that is, WARSHIP. Moreover, we give a biological overview of WARSHIP, emphasizing brain-inspired computing of WARSHIP. As a step towards WARSHIP, our case study of image super resolution combines 3 components of RSH to deploy a CNN model of WARSHIP-XZNet, which performs a happy medium between speed and performance.

Ming Zhang

Papers

Theory of Generative Deep Learning II:Probe Landscape of Empirical Error via Norm Based Capacity Control

Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution

Towards WARSHIP: Combining Components of Brain-Inspired Computing of RSH for Image Super Resolution

Study on SKA Image Deconvolution Using Deep Learning