In this video conference, two new algorithms for learning Feed-Forward Artificial Neural Network are presented. In the introduction, a brief description of the development of the existing algorithms and their flaws are shown. The second part describes the first new algorithm - Bipropagation. The basic idea is given first, followed by a detailed description of the algorithm. In the third part yet another new algorithm is given, called Border Pairs Method. Again is first given a basic idea and then follows a detailed description of the algorithm. In the fourth part, the results and findings of experimental work are presented. In the conclusion, it is found that two described algorithms are fast and reliable - the second one is also constructive.
Bojan PLOJ, PhD
Born 1965 in Maribor, Slovenia, Europe
Thesis Border Pairs Method for learning of neural network
Job 1 year R&D engineer at Birostroj Computers
10 years teaching at Electronics high school in Ptuj
4 years assistant professor University of Maribor
7 years lecturer at Higher vocational college Ptuj
3 years lecturer at the college of Ptuj (Artificial intelligence)
Voice recognition with NN
Hexapod gait control with NN
Bipropagation algorithm for learning NN
Border pairs method for learning NN
These days, the publishing house Nova Publishers published the book, entitled Advances in Machine Learning Research. In it is a chapter entitled OPTIMIZATION FOR MULTI LAYER PERCEPTRON: WITHOUT THE GRADIENT where I describe two new algorithms for neural networks learning (Bipropagation and Border Pairs Method ). Both of them are much more powerful than their predecessors - Backpropagation algorithm. The second algorithm is among other things constructive. Abstract of the book chapter
During the last twenty years, gradient-based methods have been primarily focused on the Feed Forward Artificial Neural Network learning field. They are the derivatives of Backpropagation method with various deficiencies. Some of these include an inability to: cluster and reduce noise, quantify data quality information, redundant learning data elimination. Other potential areas for improvement have been identified; including, random initialization of values of free parameters, dynamic learning from new da…
Ko sem med raziskovanjem za potrebe podiplomskega študija dobil idejo za nov algoritem strojnega učenja, me je prevzel notranji nemir. Zaslutil sem, da sem na sledi pomembnega odkritja in v hipu sem začutil kako se mi po žilah pretaka adrenalin. Pravijo, da je raziskovalna strast lahko večja celo od tiste hazarderske, ki je menda zakrivila številne zgodbe iz črne kronike. No, na vso srečo pa raziskovalna strast ni povezana s tako nizkotnimi pobudami kot hazarderska.
Ideji algoritma je nato sledil njegov razvoj, ki je trajal več kot leto in je bil prežet s številnimi vzponi in padci. Navidezne težavice so pogosto preraščale v težave, a na srečo se je vedno našla rešitev za njih. V meni sta se tako prepletala dvom in radost, dokler eksperimenti niso potrdili vseh mojih pričakovanj. Takrat so me preplavili prijetni občutki vznesenosti, ki bi jih lahko primerjali z nekakšno zaljubljenostjo. Ko si vznesen si stvarnost slikaš lepšo, kot je v resnici in tako sem naivno pričakoval, …
I have been an invited speaker at "IBM developers conference 2018" and at "IBM research lab" which is both located in Zurich (Switzerland, Europe) where I have presented three new Deep Learning Algorithms (click to view). One of them (Border Pairs Method) has 11 advantages over the famous Backpropagation. The audience was large, the response was good and was followed by a lively debate.