Assessing Architectural Similarity in Populations of Deep Neural Networks
Evolutionary deep intelligence has recently shown great promise for producing small, powerful deep neural network models via the synthesis of increasingly efficient architectures over successive generations. Despite recent research showing the efficacy of multi-parent evolutionary synthesis, little has been done to directly assess architectural similarity between networks during the synthesis process for improved parent network selection. In this work, we present a preliminary study into quantifying architectural similarity via the percentage overlap of architectural clusters. Results show that networks synthesized using architectural alignment (via gene tagging) maintain higher architectural similarities within each generation, potentially restricting the search space of highly efficient network architectures.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hidden Heterogeneity: When to Choose Similarity-Based Calibration
Trustworthy classifiers are essential to the adoption of machine learning predictions in many real-world settings. The predicted probability of possible outcomes can inform high-stakes decision making, particularly when …
Classifier calibrationDecision MakingDiagnosticThe Triangle of Similarity: A Multi-Faceted Framework for Comparing Neural Network Representations
Comparing neural network representations is essential for understanding and validating models in scientific applications. Existing methods, however, often provide a limited view. We propose the Triangle of Similarity, a …
Interpreting 16S metagenomic data without clustering to achieve sub-OTU resolution
The standard approach to analyzing 16S tag sequence data, which relies on clustering reads by sequence similarity into Operational Taxonomic Units (OTUs), underexploits the accuracy of modern sequencing technology. We pr…
ClusteringTAGTime SeriesTime Series AnalysisAssessing Intervention Strategies for Non Homogeneous Populations Using a Closed Form Formula for R0
A general stochastic model for susceptible -> infective -> recovered (SIR) epidemics in non homogeneous populations is considered. The heterogeneity is a very important aspect here since it allows more realistic but also…
FormAssessing External Validity Over Worst-case Subpopulations
Study populations are typically sampled from limited points in space and time, and marginalized groups are underrepresented. To assess the external validity of randomized and observational studies, we propose and evaluat…
Causal Inferencevalid