Interpretable Models in ANNs
Artificial neural networks are often very complex and too deep for a human to understand. As a result, they are usually referred to as black boxes. For a lot of real-world problems, the underlying pattern itself is very complicated, such that an analytic solution does not exist. However, in some cases, laws of physics, for example, the pattern can be described by relatively simple mathematical expressions. In that case, we want to get a readable equation rather than a black box. In this paper, we try to find a way to explain a network and extract a human-readable equation that describes the model.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
YANNs: Y-wise Affine Neural Networks for Exact and Efficient Representations of Piecewise Linear Functions
This work formally introduces Y-wise Affine Neural Networks (YANNs), a fully-explainable network architecture that continuously and efficiently represent piecewise affine functions with polytopic subdomains. Following fr…
Model Predictive ControlIncremental Bounded Model Checking of Artificial Neural Networks in CUDA
Artificial Neural networks (ANNs) are powerful computing systems employed for various applications due to their versatility to generalize and to respond to unexpected inputs/patterns. However, implementations of ANNs for…
GPUGPEX, A Framework For Interpreting Artificial Neural Networks
The analogy between Gaussian processes (GPs) and deep artificial neural networks (ANNs) has received a lot of interest, and has shown promise to unbox the blackbox of deep ANNs. Existing theoretical works put strict assu…
Gaussian ProcessesGPUA Machine Learning Approach for Modelling Parking Duration in Urban Land-use
Parking is an inevitable issue in the fast-growing developing countries. Increasing number of vehicles require more and more urban land to be allocated for parking. However, a little attention has been conferred to the p…
BIG-bench Machine LearningManagementReinforcement Learning-based Control via Y-wise Affine Neural Networks (YANNs)
This work presents a novel reinforcement learning (RL) algorithm based on Y-wise Affine Neural Networks (YANNs). YANNs provide an interpretable neural network which can exactly represent known piecewise affine functions …
Reinforcement Learning