Intelligence plays dice: Stochasticity is essential for machine learning
Many fields view stochasticity as a way to gain computational efficiency, while often having to trade off accuracy. In this perspective article, we argue that stochasticity plays a fundamentally different role in machine learning (ML) and is likely a critical ingredient of intelligent systems. As we review the ML literature, we notice that stochasticity features in many ML methods, affording them robustness, generalizability, and calibration. We also note that randomness seems to be prominent in biological intelligence, from the spiking patterns of individual neurons to the complex behavior of animals. We conclude with a discussion of how we believe stochasticity might shape the future of ML.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningComputational EfficiencySimilar Papers 제목 키워드 기반
Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines
Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex. Here, we introduce Synaptic Sampling Machines, a class of neural network model…
From SHAP Scores to Feature Importance Scores
A central goal of eXplainable Artificial Intelligence (XAI) is to assign relative importance to the features of a Machine Learning (ML) model given some prediction. The importance of this task of explainability by featur…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Feature Importancefeature selectionCompressed Predictive Information Coding
Unsupervised learning plays an important role in many fields, such as artificial intelligence, machine learning, and neuroscience. Compared to static data, methods for extracting low-dimensional structure for dynamic dat…
Mutual Information EstimationX-model: Improving Data Efficiency in Deep Learning with A Minimax Model
To mitigate the burden of data labeling, we aim at improving data efficiency for both classification and regression setups in deep learning. However, the current focus is on classification problems while rare attention h…
Age EstimationmodelObject Recognitionregression+1Enhancing MRI Brain Tumor Segmentation with an Additional Classification Network
Brain tumor segmentation plays an essential role in medical image analysis. In recent studies, deep convolution neural networks (DCNNs) are extremely powerful to tackle tumor segmentation tasks. We propose in this paper …
Brain Tumor SegmentationClassificationGeneral ClassificationMedical Image Analysis+2