Call For Papers
Contact Us

  Brain Intelligence: Another Aspect of Artificial Intelligence  
  Authors : Divya Bharti
  Cite as:


Artificial intelligence has captured all the activities of our daily life, it not only solve our social problems but also helps in the development of a country. From agriculture to Robot Technology (RT), AI is the key for development. AI basically works on pat-terns, learning from past experiences and then implementing them, which sometimes add as a constraint. So, in this paper we will see the different aspect of AI, that is Brain intelligence, where without the past experience also machine will be able to take logical decision.


Published In : IJCSN Journal Volume 8, Issue 1

Date of Publication : February 2019

Pages : 110-114

Figures :--

Tables : --


Divya Bharti : is a Student of Bits, Pilani Pursuing Masters in Software Systems with Specialisation in Data Analytics. She has more than 5 years of experience with IBM India and DXC technology exploring different domains of analytics. She has presented the paper in IBM for Migration of Mainframes in Cloud. Her current field of interest is AI.


Artificial Intelligence, Brain Intelligence, Robot Technology, Patterns

In this paper, I have presented state-of-the-art artificial intelligence tools for individual application areas, such as natural language processing and visual recognition. The main contributions of this work are as follows. First, this is an overview of current deep learning methods. We have summarized the nine potential applications in detail. Sec-ond, this paper puts together all the problems of recent AI models, which will direct future work for researchers. Third, in this paper, we first proposed the brain intelli-gence model, which is a model fusing artificial intelligence and artificial life. AL models, such as the S- system, have the benefits of an association function, which is different from generative adversarial networks (GAN), for building big data within a life evolution process. It is foreseeable that the BI model can solve the issues of the frame prob-lem, the association function problem, the symbol ground-ing problem, and the mental/ physical problem.


1. Y. Taigman, M. Yang, M. Ranzato, L. Wolf, "DeepFace: Closing the Gap to Human-Level Performance in Face Verification," IEEE International Conference on Comput-er Vision and Pattern Recognition (CVPR2014), pp.1-8, 2014. 2. Stanford Artificial Intelligence Laboratory,http : / /ai.stanford. edu / ( Accessed on 2017/4/20). 3. MIT BigDog, https://slice.mit.edu/big-dog/ (Accessed on 2017/4/20). 4. The 4th Science and Technology Basic Plan of Japan, http://www8.cao.go.jp/cstp/ english/basic/ 5. M. Khan, D. Lester, L. Plana, A. Rast, X. Jin, E. Painkras, S. Furber, "SpiiNNaker: Mapping neural networks onto a massively-parallel chip multiprocessor," In Proc of IEEE International JoinT Conference on Neural Net-work 6. M. Lacity, L. Willcocks, "A new approach to automating services," MIT Sloan Management Review, vol.2016, pp.1-16, 2016. 7. T Mikolov, M. Karafiat, L. Burget, J. Cernocky, S. Khu-danpur, "Recurrent neural network based language mod-el," In Proc of Interspeech2010, pp.1045-1048, 2010. 8. M. Schuster, K. Paliwal, "Bidirectional recurrent neural networks," IEEE Transactions on Signal Processing, vol.45, no.11, pp.2673-2681, 1997. 9. A. Graves, N. Jaitly, A. Mohamed, "Hybrid speech recognition with deep bidirectional LSTM,"In Proc of IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 1-4, 2013.