Followed Journals
Journal you Follow: 0
Sign Up to follow journals, search in your chosen journals and, optionally, receive Email Alerts when new issues of your Followed Journals are published.
Already have an account? Sign In to see the journals you follow.
Similar Journals
Journal Cover
Cognitive Computation and Systems
Number of Followers: 3  

  This is an Open Access Journal Open Access journal
ISSN (Print) 2517-7567 - ISSN (Online) 2517-7567
Published by IET Homepage  [46 journals]
  • Gender identification based on human brain structural MRI with a
           multi-layer 3D convolution extreme learning machine

    • Authors: Dewen Hu;Zhiguo Luo;Longfei Zhao;
      Pages: 91 - 96
      Abstract: Previous group-level neuroimaging studies have shown significant gender differences in the human brain. Research on sex-specific brain differences in healthy individuals is an important base for understanding sex-specific expression in psychiatric disorders. This study proposes a multi-layer 3D convolution extreme learning machine (MCN-ELM) to classify male and female brains based on structural MRI (sMRI) grey matter (GM) data scans from human connectome projects (HCP) of 876 healthy adults (491 females). First, the authors extracted multi-scale features by three-scale multi-layer 3D convolution neural networks (CNNs) without fine-tuning the parameters of convolution kernels. Then, they pulled the network output feature maps into a vector as separate ELMs. By voting on the three-scale networks, the MCN-ELM algorithm classifies male and female brains with an accuracy of 98.06% through a 10-fold cross-validation strategy, outperforming other state-of-the-art algorithms. The proposed method may be used to understand other brain diseases. Additionally, the results show that the human brain can be categorised into two distinct classes, male and female brains, suggesting it is better to treat men and women separately when researching psychiatric disorders.
      PubDate: 12 2019
      Issue No: Vol. 1, No. 4 (2019)
  • Improved softmax loss for deep learning-based face and expression

    • Authors: Jiancan Zhou;Xi Jia;Linlin Shen;Zhenkun Wen;Zhong Ming;
      Pages: 97 - 102
      Abstract: In recent years, deep convolutional neural networks (CNN) have been widely used in computer vision and significantly improved the performance of image recognition tasks. Most works use softmax loss to supervise the training of CNN and then adopt the output of last layer as features. However, the discriminative capability of the softmax loss is limited. Here, the authors analyse and improve the softmax loss by manipulating the cosine value and input feature length. As the approach does not change the principle of the softmax loss, the network can easily be optimised by typical stochastic gradient descent. The MNIST handwritten digits dataset is employed to visualise the features learned by the improved softmax loss. The CASIA-WebFace and FER2013 training set are adopted to train deep CNN for face and expression recognition, respectively. Results on both the LFW dataset and FER2013 test set show that the proposed softmax loss can learn more discriminative features and achieve better performance.
      PubDate: 12 2019
      Issue No: Vol. 1, No. 4 (2019)
  • Disentanglement in conceptual space during sensorimotor interaction

    • Authors: Junpei Zhong;Tetsuya Ogata;Angelo Cangelosi;Chenguang Yang;
      Pages: 103 - 112
      Abstract: The disentanglement of different objective properties from the external world is the foundation of language development for agents. The basic target of this process is to summarise the common natural properties and then to name it to describe those properties in the future. To realise this purpose, a new learning model is introduced for the disentanglement of several sensorimotor concepts (e.g. sizes, colours and shapes of objects) while the causal relationship is being learnt during interaction without much a priori experience and external instructions. This learning model links predictive deep neural models and the variational auto-encoder (VAE) and provides the possibility that the independent concepts can be extracted and disentangled from both perception and action. Moreover, such extraction is further learnt by VAE to memorise their common statistical features. The authors examine this model in the affordance learning setting, where the robot is trying to learn to disentangle about shapes of the tools and objects. The results show that such a process can be found in the neural activities of the $beta $β-VAE unit, which indicate that using similar VAE models is a promising way to learn the concepts, and thereby to learn the causal relationship of the sensorimotor interaction.
      PubDate: 12 2019
      Issue No: Vol. 1, No. 4 (2019)
  • Cognitive science and artificial intelligence: simulating the human mind
           and its complexity

    • Authors: Mohd Naveed Uddin;
      Pages: 113 - 116
      Abstract: This study encompassed around the interdisciplinary study of cognitive science in the field of artificial intelligence. Past as well as current areas of research have been highlighted such that better understating of the topic can be ensured. Furthermore, some of the present-day applications of cognitive science artificial intelligence have been discussed as these can be considered as the foundation for further improvement. Prior to discussion about future scopes, real-time complexities have been revealed.
      PubDate: 12 2019
      Issue No: Vol. 1, No. 4 (2019)
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762

Your IP address:
Home (Search)
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-