Visualizations of the training process of neural networks (CROSBI ID 685325)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Babić, Karlo ; Meštrović, Ana
engleski
Visualizations of the training process of neural networks
In this paper we present an approach to the visualizations of the neural networks training process. The main goal of such visualizations is to better understand the training process of neural networks, and to help with the creation and optimization of new neural networks. We implemented a tool which can be used to create a large number of visualizations by using different combinations of created transformations (for example: diff, plot2, angle-path, vec-dist-dev). To be able to visualize the learning process, we had to record all the weights from every n th iteration. For experiments we used three neural networks: a neural network for digit recognition (DR), a neural network for word2vec representation of words (WV), and a neural network which learned the simple logical gate XOR, (XR). For the purpose of further comparisons, we also constructed one example of a damaged network (DR', WV', XR') for each of the three original networks (DR, WV, XR). We constructed over 30 visualizations and then chose 6 visualizations which could be easily interpreted and present them in this paper. The results indicate that there may exist some regularities in the visualizations of original networks and that damaged network visualizations differ from the original networks.
data visualisation ; learning (artificial intelligence) ; logic gates ; natural language processing ; neural nets ; optimisation ; statistical analysis ; text analysis
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1619-1623.
2019.
objavljeno
10.23919/MIPRO.2019.8757142
Podaci o matičnoj publikaciji
2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)
Biljanović, Petar
Opatija: Institute of Electrical and Electronics Engineers (IEEE)
2623-8764
Podaci o skupu
MIPRO 2019
predavanje
20.05.2019-24.05.2019
Opatija, Hrvatska
Povezanost rada
Informacijske i komunikacijske znanosti, Računarstvo