Artificial Intelligence

<Note> More contents will be added soon. Check back soon !

Introduction

Updated: 27 Nov 2019 01:00AM

Artificial Intelligence (AI) and Machine Learning (ML) are two very trendy buzzwords for many years. AI and ML are often seem to be used interchangeably, however (technically) they are not so quite the same thing.

Artificial Intelligence

  • Broader concept of machines being able to carry out smart tasks

Machine Learning

  • Application of AI that human give machines access to data and let machines learn for themselves.

Sub-fields in Artificial Intelligence

  1. Artificial General Intelligence (AGI)
  2. Automated planning and scheduling (AI planning)
  3. Computer vision
  4. Knowledge Representation and Reasoning (KR², KR&R)
  5. Machine Learning (ML)
  6. Natural Language Processing (NLP)
  7. Robotics (click here to read the Robotics sections)


Types of Machine Learning

  1. Supervised
  2. Unsupervised
  3. Reinforcement


Machine Learning in the Cloud

  1. Google Cloud ML Engine
  2. Amazon Machine Learning (AML)
  3. Azure Machine Learning Studio

Publications

Highly Cited AI /ML Related Publications

Carl Edward Rasmussen, "Gaussian Processes in Machine Learning," Advanced Lectures on Machine Learning, pp. 63-71, 2004. DOI: 10.1007/978-3-540-28650-9_4

  • Abstract: We give a basic introduction to Gaussian Process regression models. We focus on understanding the role of the stochastic process and how it is used to define a distribution over functions. We present the simple equations for incorporating training data and examine how to learn the hyperparameters using the marginal likelihood. We explain the practical advantages of Gaussian Process and end with conclusions and a look at the current trends in GP work.
  • Citation: 16.9k+ [link]
  • Semantic Scholar: 2371 Highly Influenced Papers

Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, Édouard Duchesnay, "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp.2825-2830 , 2011.

  • Abstract: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from http://scikit-learn.sourceforge.net .
  • Citation: 26.7k+ [link]
  • Semantic Scholar: 856 Highly Influenced Papers

Notable I2R AI / ML Related Publications

Xiaoli Li, Min Wu, Chee-Keong Kwoh, and See-Kiong Ng, "Computational approaches for detecting protein complexes from protein interaction networks: a survey," in Proc. of International Workshop on Computational Systems Biology: Approaches to Analysis of Genome Complexity and Regulatory Gene Networks, BMC Genomics, vol. 11, sup. 1, Feb. 2010. DOI: 10.1186/1471-2164-11-S1-S3

  • Abstract:
    • Most proteins form macromolecular complexes to perform their biological functions. However, experimentally determined protein complex data, especially of those involving more than two protein partners, are relatively limited in the current state-of-the-art high-throughput experimental techniques. Nevertheless, many techniques (such as yeast-two-hybrid) have enabled systematic screening of pairwise protein-protein interactions en masse. Thus computational approaches for detecting protein complexes from protein interaction data are useful complements to the limited experimental methods. They can be used together with the experimental methods for mapping the interactions of proteins to understand how different proteins are organized into higher-level substructures to perform various cellular functions.
    • Given the abundance of pairwise protein interaction data from high-throughput genome-wide experimental screenings, a protein interaction network can be constructed from protein interaction data by considering individual proteins as the nodes, and the existence of a physical interaction between a pair of proteins as a link. This binary protein interaction graph can then be used for detecting protein complexes using graph clustering techniques. In this paper, we review and evaluate the state-of-the-art techniques for computational detection of protein complexes, and discuss some promising research directions in this field.
    • Experimental results with yeast protein interaction data show that the interaction subgraphs discovered by various computational methods matched well with actual protein complexes. In addition, the computational approaches have also improved in performance over the years. Further improvements could be achieved if the quality of the underlying protein interaction data can be considered adequately to minimize the undesirable effects from the irrelevant and noisy sources, and the various biological evidences can be better incorporated into the detection process to maximize the exploitation of the increasing wealth of biological knowledge available.
  • Citation: 0.3k+ [link]
  • Semantic Scholar: 18 Highly Influenced Papers
  • This is an Open Access article

Jian Bo Yang, Minh Nhut Nguyen, Phyo Phyo San, Xiao Li Li, and Shonali Krishnaswamy, "Deep Convolutional Neural Networks On Multichannel Time Series For Human Activity Recognition," in Proc. of Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015), pp. 3995-4001, Jul. 2015.

  • Abstract: This paper focuses on human activity recognition (HAR) problem, in which inputs are multichannel time series signals acquired from a set of bodyworn inertial sensors and outputs are predefined human activities. In this problem, extracting effective features for identifying activities is a critical but challenging task. Most existing work relies on heuristic hand-crafted feature design and shallow feature learning architectures, which cannot find those distinguishing features to accurately classify different activities. In this paper, we propose a systematic feature learning method for HAR problem. This method adopts a deep convolutional neural networks (CNN) to automate feature learning from the raw inputs in a systematic way. Through the deep architecture, the learned features are deemed as the higher level abstract representation of low level raw time series signals. By leveraging the labelled information via supervised learning, the learned features are endowed with more discriminative power. Unified in one model, feature learning and classification are mutually enhanced. All these unique advantages of the CNN make it outperform other HAR algorithms, as verified in the experiments on the Opportunity Activity Recognition Challenge and other benchmark datasets.
  • Citation: 0.4k+ [link]
  • Semantic Scholar: 24 Highly Influenced Papers
  • Download link: https://www.ijcai.org/Proceedings/15/Papers/561.pdf

AI / ML People

Influential AI / ML Researcher in Singapore

Listed in alphabetical order by given name
  • Professor Weisi Lin, School of Computer Science and Engineering, Nanyang Technological University [ref]
    • Fellow of IET
    • Honorary Fellow of SIET
    • IEEE Fellow for the contribution to perceptual modeling and processing of visual signals (2016)


  • Adjunct Associate Professor Xiaoli Li, Nanyang Technological University [ref]
    • Head, Machine Intellection, Institute for Infocomm Research (I2R) [ref]


  • Professor Yap Peng Tan, School of Electrical & Electronic Engineering, Nanyang Technological University [ref]
    • IEEE Fellow for the contribution to visual data analysis and processing (2019)


  • President’s Chair Professor Yew-Soon Ong, School of Computer Science and Engineering, Nanyang Technological University [ref]
    • Chief Artificial Intelligence Scientist, A*STAR [ref]
    • Thomson Reuters lists him as a Highly Cited researcher and among the World's Most Influential Scientific Minds
    • Scientific Advisor, Singapore Digital Economy Initiative, National Research Foundation (NRF)
    • IEEE Fellow for the contribution to memetic computation and applications (2018)

Inspiring AI / ML Researcher in Singapore

Listed in alphabetical order by given name
  • Scientist, Dr. Shili Xiang, Department of Data Analytics, Institute for Infocomm Research (I2R) [ref] [ref2] [ref3]

References

Online Artificial Intelligence Articles

  • Marr, Bernard (2016, Dec. 6). What Is The Difference Between Artificial Intelligence And Machine Learning? Retrieved Nov. 24, 2019 from Forbes

Keywords

artificial intelligence, machine learning, I2R AI, I2R data analytic, data mining, big data, Scikit-learn, TensorFlow, Accord.NET, Apache Mahout, Apache Spark MLlib, Matplotlib, NTU, research, science, Singapore

Tags

#AI #DA #regression #TensorFlow #MLlib #singapore