paper-with-me

홈 › Papers

A Differentiable Transition Between Additive and Multiplicative Neurons

2016-04-13 · Wiebke Köpp, Patrick van der Smagt, Sebastian Urban

Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform. However, this leads to an extensive increase in the computational complexity of the training procedure. We present a novel, parameterizable transfer function based on the mathematical concept of non-integer functional iteration that allows the operation each neuron performs to be smoothly and, most importantly, differentiablely adjusted between addition and multiplication. This allows the decision between addition and multiplication to be integrated into the standard backpropagation training procedure.

📄 PDF Abstract BibTeX arXiv:1604.03736

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Neural Transfer Function for a Smooth and Differentiable Transition Between Additive and Multiplicative Interactions

2015-03-19 · Sebastian Urban, Patrick van der Smagt

Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform. This leads eit…

Equivalence of Additive and Multiplicative Coupling in Spiking Neural Networks

2023-03-31 · Georg Börner, Fabio Schittler Neves, Marc Timme

Spiking neural network models characterize the emergent collective dynamics of circuits of biological neurons and help engineer neuro-inspired solutions across fields. Most dynamical systems' models of spiking neural net…

An exact solution in Markov decision process with multiplicative rewards as a general framework

2020-12-15 · Yuan YAO, Xiaolin Sun

We develop an exactly solvable framework of Markov decision process with a finite horizon, and continuous state and action spaces. We first review the exact solution of conventional linear quadratic regulation with a lin…

Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

2013-08-15 · Yoshua Bengio, Nicholas Léonard, Aaron Courville

Stochastic neurons and hard non-linearities can be useful for a number of reasons in deep learning models, but in many cases they pose a challenging problem: how to estimate the gradient of a loss function with respect t…

Theory of gating in recurrent neural networks

2020-07-29 · Kamesh Krishnamurthy, Tankut Can, David J. Schwab

Recurrent neural networks (RNNs) are powerful dynamical models, widely used in machine learning (ML) and neuroscience. Prior theoretical work has focused on RNNs with additive interactions. However, gating - i.e. multipl…