58 citations · 67 across the 8 of their papers we have counts for
10 papers
Uninorm-like parametric activation functions for human-understandable neural models
Orsolya Csiszár, Luca Sára Pusztaházi, Lehel Dénes-Fazakas +3
We present a deep learning model for finding human-understandable connections between input features. Our approach uses a parameterized, differentiable activation function, based o…
Leveraging Product as an Activation Function in Deep Networks
Luke B. Godfrey, Michael S. Gashler
Product unit neural networks (PUNNs) are powerful representational models with a strong theoretical basis, but have proven to be difficult to train with gradient-based optimizers.…
A parameterized activation function for learning fuzzy logic operations in deep neural networks
Luke B. Godfrey, Michael S. Gashler
We present a deep learning architecture for learning fuzzy logic expressions. Our model uses an innovative, parameterized, differentiable activation function that can learn a numbe…
Deep Learning in Robotics: A Review of Recent Research
Harry A. Pierson, Michael S. Gashler
Advances in deep learning over the last decade have led to a flurry of research in the application of deep artificial neural networks to robotic systems, with at least thirty paper…
Neural Decomposition of Time-Series Data for Effective Generalization
Luke B. Godfrey, Michael S. Gashler
We present a neural network technique for the analysis and extrapolation of time-series data called Neural Decomposition (ND). Units with a sinusoidal activation function are used…
A continuum among logarithmic, linear, and exponential functions, and its potential to improve generalization in neural networks
Luke B. Godfrey, Michael S. Gashler
We present the soft exponential activation function for artificial neural networks that continuously interpolates between logarithmic, linear, and exponential functions. This activ…
A Minimal Architecture for General Cognition
Michael S. Gashler, Zachariah Kindle, Michael R. Smith
A minimalistic cognitive architecture called MANIC is presented. The MANIC architecture requires only three function approximating models, and one state machine. Even with so few m…
A Hybrid Latent Variable Neural Network Model for Item Recommendation
Michael R. Smith, Tony Martinez, Michael Gashler
Collaborative filtering is used to recommend items to a user without requiring a knowledge of the item itself and tends to outperform other techniques. However, collaborative filte…
Training Deep Fourier Neural Networks To Fit Time-Series Data
Michael S. Gashler, Stephen C. Ashmore
We present a method for training a deep neural network containing sinusoidal activation functions to fit to time-series data. Weights are initialized using a fast Fourier transform…
Missing Value Imputation With Unsupervised Backpropagation
Michael S. Gashler, Michael R. Smith, Richard Morris +1
Many data mining and data analysis techniques operate on dense matrices or complete tables of data. Real-world data sets, however, often contain unknown values. Even many classific…