ARTIFICIAL INTELLIGENCE

Bipropagation is a new Deep Learning algorithm. It is much faster and much more reliable than Backpropagation. Here is the demo from the  ResearchGate and GitHub. Inner layers of the Neural Network have not hidden anymore. Learning is done layer by layer with much fewer iterations. Please cite me in your work. Click the G+   button if you like this demo. Any comments are desirable.

Raziskovalci se občasno sestanemo, da drug drugemu predstavimo svoje delo, svoje dosežke. Dobra priložnost za to so znanstvene konference. Ena naj bolj uglednih tovrstnih konferenc na področju umetne inteligence v Sloveniji z naslovom Informacijska družba 2016 , se je odvila te dni na institutu Jožef Štefan v Ljubljani. Na njej smo obravnavali mnogo zanimivih tem, ki nam nakazujejo smer razvoja informacijske tehnologije v družbi v bližnji prihodnosti. Zadnja leta je vedno bolj v ospredju umetna inteligenca in strojno učenje, trenutno v svetu še posebej odmevajo dosežki globokega učenja. Nekatere druge teme so bile: evidentiranje genetsko modificiranih organizmov v živilih, zaznavanje stresa v službi, priporočanje čtiva, odkrivanje novih zlitin, sinteza slovenskega govora, razvoj avtonomnega vozila; seveda vse skupaj na osnovi umetne inteligence. Sam sem predstavil kolegom dva nova algoritma strojnega učenja, ki sem ju razvil v bližnji preteklosti. Več o vsebini ...

Here is given an example of the "bipropagation" algorithm for learning of NN. It is written in MatLAB language (R2015a) and is as similar as possible  to  "Deep learning" example "AutoencoderDigitsExample.m" which is included in MatLAB's Neural Network Toolbox. So you can easily compare both algorithms. I believe that my algorithm have few advantages over autoencoder. Please tell me what do you think about it. Please cite me in your works. Thanks a lot. Download demo ====================================================== %% Training a Deep Neural Network for Digit Classification % This example shows how to use the Neural Network Toolbox(TM) to train a % deep neural network to classify images of digits and is very similar to % "AutoencoderDigitsExample.m" which is included in % Neuronal Network ToolBox from MatLAB. This example is made for comparison % of both algorithms. % % Neural networks with multiple hidden layers can be usefu...

Znanstvena založba Nova Science Publishers  iz New Yorka je nedavno izdala knjigo z naslovom  Advances in Machine Learning Research (Napredek v raziskavah strojnega učenja) . Tretje poglavje z naslovom    Optimization for Multi-Layer Perceptron: Without the Gradient , je  plod slovenske znanosti in   opisuje  dve novi metodi strojnega učenja. Obe sta nadgradnja zelo  uveljavljene metode Backpropagation, ki je temelj delovanja nevronskih mrež, ki so ene od najbolj razširjenih naprav na področju umetne inteligence. Novi metodi pomenita velik napredek, saj odpravljata ozko grlo umetne inteligence - izboljšujeta potek in rezultat učenja.    Prva metod se imenuje Bipropagation in je majnša izboljšava, ki omogoča mnogo hitrejše in bolj zanesljivo učenje. Druga metoda -  Metoda mejnih parov   (angleško Border Pairs Method, BPM)  je povsem izvirna   in ima številne prednosti pred metodo Backpropagation: samod...

  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 fre...

Border Pairs Method (BPM) is a new constructive method for supervised learning of multilayer perceptron (MLP), which calculates , values of weights and biases directly from the geometry of learning patterns. To determine BPM’s capabilities, we compared it with three other supervised machine learning methods: Backpropagation , SVM  and Decision Trees. The  comparison were made on six databases: XOR, Triangle, Iris, Pen-Based Recognition of Handwritten Digits, Online Pen-Based Recognition of Handwritten Digits and synthetically generated noisy data. Border Pairs Method found near minimal MLP architecture in all described cases. For classification of the Iris Setosa only two border pairs (only four patterns out of 150) were enough for learning the whole data set correctly. In the classification of ‘Pen-Based Recognition of Handwritten Digits’ dataset only 200 learning patterns were used for learning. The BPM correctly identified more than 95% from 3498 handwritten digits, ...