Search Results for author:
Found 9 papers, 0 papers with code
Deep multi-prototype capsule networks
Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically.
PowerLinear Activation Functions with application to the first layer of CNNs
One way to increase the capability of the convolution operator is by applying activation functions on the inner product operator.
Neural Generalization of Multiple Kernel Learning
By this interpretation, we propose a Neural Generalization of Multiple Kernel Learning (NGMKL), which extends the conventional multiple kernel learning framework to a multi-layer neural network with nonlinear activation functions.
Prototype-based interpretation of the functionality of neurons in winner-take-all neural networks
We propose a novel training algorithm for the $\pm$ED-WTA network, which cleverly switches between updating the positive and negative prototypes and is essential to the emergence of interpretable prototypes.
Improving the Backpropagation Algorithm with Consequentialism Weight Updates over Mini-Batches
Many attempts took place to improve the adaptive filters that can also be useful to improve backpropagation (BP).
Learning 2D Gabor Filters by Infinite Kernel Learning Regression
In this paper, we prove that 2D Gabor functions are translation-invariant positive-definite kernels and propose a novel formulation for the problem of image representation with Gabor functions based on infinite kernel learning regression.
Generalizing the Convolution Operator in Convolutional Neural Networks
The second one is the class of similarity measures defined based on a distance function.
Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification
Experimental results on two gesture recognition tasks show that the proposed method outperforms LDCRFs, hidden Markov models, and conditional random fields.
A two-stage learning method for protein-protein interaction prediction
In the proposed method, the denoising auto encoders are employed for learning robust features.
