Results 251 to 260 of about 10,684,153 (270)

The impact of dynamic reversal potential on the evolution of action potential attributes during spike trains. [PDF]

Front Comput Neurosci
Aldohbeyb AA, Vigh J, Lear KL.
europepmc   +1 more source

WiggleGPT: Revisiting the Monotonicity Assumption in Neural Networks via Oscillating Activation Functions

O'brien, Phillip
openalex   +1 more source

Some of the next articles are maybe not open access.

Related searches:

ConcaveQ: Non-Monotonic Value Function Factorization via Concave Representations in Deep Multi-Agent Reinforcement Learning

AAAI Conference on Artificial Intelligence, 2023
Value function factorization has achieved great success in multi-agent reinforcement learning by optimizing joint action-value functions through the maximization of factorized per-agent utilities.
Huiqun Li, Hanhan Zhou, Yifei Zou, Dongxiao Yu, Tian Lan   +4 more
semanticscholar   +1 more source

Effort is Not a Monotonic Function of Skills: Results from a Global Mobile Experiment

Journal of Economic Behavior and Organization, 2020
At the core of economic theory is the monotonicity hypothesis: an agent’s effort, as a function of their skills, is either non-decreasing or non-increasing, but not both.
Konrad Grabiszewski, A. Horenstein
semanticscholar   +1 more source

Mish: A Self Regularized Non-Monotonic Activation Function

British Machine Vision Conference, 2020
We propose Mish , a novel self-regularized non-monotonic activation function which can be mathematically defined as: f ( x ) = x tanh ( softplus ( x )) .
Diganta Misra
semanticscholar   +1 more source

Shifted Inverse: A General Mechanism for Monotonic Functions under User Differential Privacy

Conference on Computer and Communications Security, 2022
While most work on differential privacy has focused on protecting the privacy of tuples, it has been realized that such a simple model cannot capture the complex user-tuple relationships in many real-world applications.
Juanru Fang, Wei Dong, K. Yi
semanticscholar   +1 more source

An Off-Policy Trust Region Policy Optimization Method With Monotonic Improvement Guarantee for Deep Reinforcement Learning

IEEE Transactions on Neural Networks and Learning Systems, 2021
In deep reinforcement learning, off-policy data help reduce on-policy interaction with the environment, and the trust region policy optimization (TRPO) method is efficient to stabilize the policy optimization procedure. In this article, we propose an off-
Wenjia Meng, Qian Zheng, Yuejun Shi, Gang Pan   +3 more
semanticscholar   +1 more source