2 code implementations • 19 Feb 2022 • Cristian Ivan
We introduce an algorithm where the individual bits representing the weights of a neural network are learned.
2 code implementations • 30 Jun 2020 • Cristian Ivan, Razvan Florian
We present some novel, straightforward methods for training the connection graph of a randomly initialized neural network without training the weights.
no code implementations • 25 Jul 2019 • Cristian Ivan
Convolutional Neural Networks (CNNs) are build specifically for computer vision tasks for which it is known that the input data is a hierarchical structure based on locally correlated elements.
no code implementations • 23 May 2019 • Cristian Ivan, Bipin Indurkhya
In this paper, we argue than one of the most important aspects of the human mind is its capacity for logical thinking, which gives rise to many intellectual expressions that differentiate us from animal brains.