TY - JOUR
T1 - Deep learning adapted to differential neural networks used as pattern classification of electrophysiological signals
AU - Llorente, Dusthon
AU - Ballesteros, Mariana
AU - Salgado Ramos, Ivan DE JESUS
AU - Oria, Jorge Isaac Chairez
N1 - Publisher Copyright:
IEEE
PY - 2022/9/1
Y1 - 2022/9/1
N2 - This manuscript presents the design of a deep differential neural network (DDNN) for pattern classification. First, we proposed a DDNN topology with three layers, whose learning laws are derived from a Lyapunov analysis, justifying local asymptotic convergence of the classification error and the weights of the DDNN. Then, an extension to include an arbitrary number of hidden layers in the DDNN is analyzed. The learning laws for this general form of the DDNN offer a contribution to the deep learning framework for signal classification with biological nature and dynamic structures. The DDNN is used to classify electroencephalographic signals from volunteers that perform an identification graphical test. The classification results show exponential growth in the signal classification accuracy from 82 with one layer to 100 with three hidden layers. Working with DDNN instead of static deep neural networks (SDNN) represents a set of advantages, such as processing time and training period reduction up to almost 100 times, and the increment of the classification accuracy while working with less hidden layers than working with SDNN, which are highly dependent on their topology and the number of neurons in each layer. The DDNN employed fewer neurons due to the induced feedback characteristic.
AB - This manuscript presents the design of a deep differential neural network (DDNN) for pattern classification. First, we proposed a DDNN topology with three layers, whose learning laws are derived from a Lyapunov analysis, justifying local asymptotic convergence of the classification error and the weights of the DDNN. Then, an extension to include an arbitrary number of hidden layers in the DDNN is analyzed. The learning laws for this general form of the DDNN offer a contribution to the deep learning framework for signal classification with biological nature and dynamic structures. The DDNN is used to classify electroencephalographic signals from volunteers that perform an identification graphical test. The classification results show exponential growth in the signal classification accuracy from 82 with one layer to 100 with three hidden layers. Working with DDNN instead of static deep neural networks (SDNN) represents a set of advantages, such as processing time and training period reduction up to almost 100 times, and the increment of the classification accuracy while working with less hidden layers than working with SDNN, which are highly dependent on their topology and the number of neurons in each layer. The DDNN employed fewer neurons due to the induced feedback characteristic.
KW - Biological neural networks
KW - Complexity theory
KW - Deep learning
KW - Differential neural networks
KW - EEG classification
KW - Electroencephalography
KW - Heuristic algorithms
KW - Lyapunov stability
KW - Stability analysis
KW - Task analysis
KW - Topology
UR - http://www.scopus.com/inward/record.url?scp=85135596426&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2021.3066996
DO - 10.1109/TPAMI.2021.3066996
M3 - Artículo
C2 - 33735073
AN - SCOPUS:85135596426
SN - 0162-8828
VL - 44
SP - 4807
EP - 4818
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 9
ER -