Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
GPT-5.1
GPT-5.1 104 tok/s
Gemini 3.0 Pro 36 tok/s Pro
Gemini 2.5 Flash 133 tok/s Pro
Kimi K2 216 tok/s Pro
Claude Sonnet 4.5 37 tok/s Pro
2000 character limit reached

Classification with neural networks with quadratic decision functions (2401.10710v2)

Published 19 Jan 2024 in cs.LG, cs.NA, and math.NA

Abstract: Neural networks with quadratic decision functions have been introduced as alternatives to standard neural networks with affine linear ones. They are advantageous when the objects or classes to be identified are compact and of basic geometries like circles, ellipses etc. In this paper we investigate the use of such ansatz functions for classification. In particular we test and compare the algorithm on the MNIST dataset for classification of handwritten digits and for classification of subspecies. We also show, that the implementation can be based on the neural network structure in the software Tensorflow and Keras, respectively.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (16)
  1. ``TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems'' In arXiv, 2021 URL: https://arxiv.org/abs/1603.04467
  2. M.D. Buhmann ``Radial Basis Functions'', 2003 DOI: 10.1017/cbo9780511543241
  3. F. Chollet ``Keras'', 2015 URL: https://keras.io
  4. G. Cybenko ``Approximation by superpositions of a sigmoidal function'' In Mathematics of Control, Signals, and Systems 2.4, 1989, pp. 303–314 DOI: 10.1007/bf02551274
  5. F. Fan, J. Xiong and G. Wang ``Universal approximation with quadratic deep networks'' In Neural Networks 124, 2020, pp. 383–392 DOI: 10.1016/j.neunet.2020.01.007
  6. L. Frischauf, O. Scherzer and C. Shi ``Quadratic neural networks for solving inverse problems'', 2023 URL: https://arxiv.org/abs/2401.09445
  7. ``Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups'' In IEEE Signal Processing Magazine 29.6, 2012, pp. 82–97 DOI: 10.1109/msp.2012.2205597
  8. A. Krizhevsky, I. Sutskever and G.E. Hinton ``ImageNet classification with deep convolutional neural networks'' In Communications of the Association for Computing Machinery 60.6, 2017, pp. 84–90 DOI: 10.1145/3065386
  9. Y. LeCun ``The MNIST database of handwritten digits'' Microsoft Research Lab – Redmond, 1998
  10. ``Comparison of learning algorithms for handwritten digit recognition'' In International conference on artificial neural networks 60.1, 1995, pp. 53–60
  11. ``Convolutional networks for images, speech, and time series'' In Communications of the Association for Computing Machinery 3361.10 Citeseer, 1995, pp. 255–258
  12. ``Visualizing Data using t-SNE'' In Journal of Machine Learning Research (JMLR) 9.11, 2008, pp. 2579–2605
  13. H.N. Mhaskar ``Approximation properties of a multilayered feedforward artificial neural network'' In Advances in Computational Mathematics 1.1 Springer US, 1993, pp. 61–80 DOI: 10.1007/bf02070821
  14. T.M. Mitchell ``Machine Learning'' New York: McGraw Hill Education, 1997
  15. F. Nielsen ``Introduction to HPC with MPI for Data Science'' Springer, 2016
  16. ``Neurons With Paraboloid Decision Boundaries for Improved Neural Network Classification Performance'' In IEEE Transactions on Neural Networks and Learning Systems 30.1, 2019, pp. 284–294 DOI: 10.1109/tnnls.2018.2839655

Summary

We haven't generated a summary for this paper yet.

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 1 tweet and received 0 likes.

Upgrade to Pro to view all of the tweets about this paper: