| 2004 |
| 25 | EE | Jani J. T. Lahnajärvi,
Mikko Lehtokangas,
Jukka Saarinen:
Estimating movements of a robotic manipulator by hybrid constructive neural networks.
Neurocomputing 56: 345-363 (2004) |
| 24 | EE | Arto Kantsila,
Mikko Lehtokangas,
Jukka Saarinen:
Complex RPROP-algorithm for neural network equalization of GSM data bursts.
Neurocomputing 61: 339-360 (2004) |
| 2003 |
| 23 | EE | Arto Kantsila,
Mikko Lehtokangas,
Jukka Saarinen:
On radial basis function network equalization in the GSM system.
ESANN 2003: 179-184 |
| 2002 |
| 22 | | Eero Huupponen,
Sari-Leena Himanen,
Alpo Värri,
Joel Hasan,
Antti Saastamoinen,
Mikko Lehtokangas,
Jukka Saarinen:
Fuzzy detection of EEG alpha without amplitude thresholding.
Artificial Intelligence in Medicine 24(2): 133-147 (2002) |
| 21 | EE | Jani J. T. Lahnajärvi,
Mikko Lehtokangas,
Jukka Saarinen:
Evaluation of constructive neural networks with cascaded architectures.
Neurocomputing 48(1-4): 573-607 (2002) |
| 2000 |
| 20 | | Mikko Lehtokangas:
Fast Learning Using Multilayer Perceptron Networks with Adaptive Centroid Layer.
IJPRAI 14(2): 211-224 (2000) |
| 19 | EE | Mikko Lehtokangas:
Determining the number of centroids for CMLP network.
Neural Networks 13(4-5): 525-531 (2000) |
| 18 | EE | Mikko Lehtokangas:
Modified constructive backpropagation for regression.
Neurocomputing 35(1-4): 113-122 (2000) |
| 1999 |
| 17 | EE | Mikko Lehtokangas:
Fast initialization for cascade-correlation learning.
IEEE Transactions on Neural Networks 10(2): 410-414 (1999) |
| 16 | | Petri Salmela,
Mikko Lehtokangas,
Jukka Saarinen:
Neural Network Based Digit Recognition System for Voice Dialling in Noisy Environments.
Inf. Sci. 121(3-4): 171-199 (1999) |
| 15 | EE | Mikko Lehtokangas:
Feedforward Neural Network with Adaptive Reference Pattern Layer.
Int. J. Neural Syst. 9(1): 1-9 (1999) |
| 14 | EE | Mikko Lehtokangas:
Modelling with constructive backpropagation.
Neural Networks 12(4-5): 707-716 (1999) |
| 13 | | Mikko Lehtokangas:
Constructive Backpropagation for Recurrent Networks.
Neural Processing Letters 9(3): 271-278 (1999) |
| 1998 |
| 12 | | Petri Salmela,
Mikko Lehtokangas,
Jukka Saarinen:
Noisy Digit Recognition with MLP and HMMS Using Modified Cost Function in MCE Training.
ICONIP 1998: 1118-1121 |
| 11 | | Mikko Lehtokangas:
Fast Training with Maximum Covariance Initialized Centroid MLP.
ICONIP 1998: 1385-1388 |
| 10 | | Mikko Lehtokangas:
On Training of MLP with Adaptive Neuron Specific Preprocessing Units.
ICONIP 1998: 1567-1570 |
| 9 | | Mikko Lehtokangas:
Initialization of MLP with Adaptive Neuron Specific Preprocessing Units.
ICONIP 1998: 1571-1574 |
| 8 | | Mikko Lehtokangas:
Reference Pattern Weight Initialization for Equalization.
IEA/AIE (Vol. 2) 1998: 574-581 |
| 7 | | Mikko Lehtokangas,
Jukka Saarinen:
Centroid based Multilayer Perceptron Networks.
Neural Processing Letters 7(2): 101-106 (1998) |
| 6 | EE | Antti Saastamoinen,
Timo Pietilä,
Alpo Värri,
Mikko Lehtokangas,
Jukka Saarinen:
Waveform detection with RBF network - Application to automated EEG analysis.
Neurocomputing 20(1-3): 1-13 (1998) |
| 5 | EE | Mikko Lehtokangas,
Jukka Saarinen:
Weight initialization with reference patterns.
Neurocomputing 20(1-3): 265-278 (1998) |
| 1997 |
| 4 | | Seppo Kuusisto,
Mikko Lehtokangas,
Jukka Saarinen,
Kimmo Kaski:
Short Term Electric Load Forecasting Using A Neural Network with Fuzzy Hidden Neurons.
Neural Computing and Applications 6(1): 42-56 (1997) |
| 1996 |
| 3 | | Mikko Lehtokangas,
Jukka Saarinen,
Pentti Huuhtanen,
Kimmo Kaski:
Predictive minimum description length criterion for time series modeling with neural networks.
Neural Computation 8(3): 583-593 (1996) |
| 1995 |
| 2 | EE | Mikko Lehtokangas,
Jukka Saarinen,
Kimmo Kaski:
Accelerating training of radial basis function networks with Cascade-Correlation algorithm.
Neurocomputing 9(2): 207-213 (1995) |
| 1993 |
| 1 | | Mikko Lehtokangas,
Jukka Saarinen,
Pentti Huuhtanen,
Kimmo Kaski:
Neural Network Optimization Tool Based on Predictive MDL Principle for Time Series Prediction.
ICTAI 1993: 338-342 |