Preskoči na glavno vsebino

Novosti strojnega učenja

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:

  • samodejno najde primerno zgradbo nevronske mreže (MLP),
  • vedno najde rešitev,
  • za učenje uporablja le ustrezne vzorce,
  • roji vzorce, 
  • poišče kvalitetne značilke,
  • omogoča kvalitetno razšumljanje in
  • že pred pričetkom učenja  ugotovi kako zahtevni so učni vzorci.


Čas bo pokazal kako se bodo na noviteti odzvali znanstveniki in gospodarstveniki. Prvi odzivi znanstvene skupnosti so zelo dobri. Če ti je ta sestavek všečen, klikni G+ spodaj!

  

Komentarji

Priljubljene objave iz tega spletnega dnevnika

Bipropagation demo in TensorFlow

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.

A new Deep Learning Algorithm: One-Step Method

We are living in the AI era where progress is faster and faster each and every single day. Here is another one discovery in this field: One Step Method, a new machine learning algorithm which can do many things, amongst other can replace digital circuits with neurons, can find the even better construction of neural network than Border Pairs Method. More you can find in the 3rd chapter of our book: Machine Learning: Advances in Research and Applications from Nova Science Publishers.




This new algorithm is also suitable for Deep Learning in combination with other methods like convolutional learning, bipropagation, border pairs method, autoencoder and others.

Three new Deep Learning Algorithms at IBM Developers Unconference 2018

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.