Abstract
Neural networks can deliver surprising, and sometimes unwanted, results.
- Shwartz-Ziv, R., and Tishby, N. Opening the Black Box of Deep Neural Networks via Information. ArXiv: https://arxiv.org/abs/1703.00810.Google Scholar
- Zhang, C., Bengio, S., Hardt, M., Recht, B., and Vinyalis, O. Understanding Deep Learning Requires Rethinking Generalization. ArXiV: https://arxiv.org/abs/1611.03530.Google Scholar
- Poggio, T., Liao, Q., Miranda, B., Rosasco, L., Boix, X., Hidary, J., and Mhaskar, H. Theory of Deep Learning III: Explaining the Non-Overfitting Puzzle. CBMM Memo 073 (2017). https://cbmm.mit.edu/sites/default/files/publications/CBMM-Memo-073.pdf.Google Scholar
- Achille, A., Rovere, M., and Soatto, S. Critical Learning Periods in Deep Neural Networks. UCLA-TR-170017. ArXiV: https://arxiv.org/abs/1711.08856.Google Scholar
Index Terms
- Deep learning hunts for signals among the noise
Recommendations
Deep learning: an overview and main paradigms
In the present paper, we examine and analyze main paradigms of learning of multilayer neural networks starting with a single layer perceptron and ending with deep neural networks, which are considered regarded as a breakthrough in the field of the ...
Instantaneous Frequency Estimation of Nonlinear Frequency-Modulated Signals Under Strong Noise Environment
Instantaneous frequency (IF) is the most important parameter of a signal, which is an important representation of non-stationary signals, such as frequency-modulated signals. Usually, signals are received with noises. Under noise environment, the ...
Experimental analysis for classification of EEG signals using deep learning framework for optimizing accuracy and cost
Electroencephalogram (EEG) signals are essential in brain-computer interface systems. Nowadays, these signals are employed in various medical applications. In the past few years, EEG signals gain more attention in security systems to identify users, as ...
Comments