Pith. sign in

REVIEW 1 cited by

The training accuracy of two-layer neural networks: its estimation and understanding using random datasets

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.13380 v2 pith:EMAQPILD submitted 2020-10-26 cs.LG cs.AImath.CO

classification cs.LGcs.AImath.CO
keywords trainingaccuracymethodmodelsneuraldatasetsestimatelearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Although the neural network (NN) technique plays an important role in machine learning, understanding the mechanism of NN models and the transparency of deep learning still require more basic research. In this study, we propose a novel theory based on space partitioning to estimate the approximate training accuracy for two-layer neural networks on random datasets without training. There appear to be no other studies that have proposed a method to estimate training accuracy without using input data and/or trained models. Our method estimates the training accuracy for two-layer fully-connected neural networks on two-class random datasets using only three arguments: the dimensionality of inputs (d), the number of inputs (N), and the number of neurons in the hidden layer (L). We have verified our method using real training accuracies in our experiments. The results indicate that the method will work for any dimension, and the proposed theory could extend also to estimate deeper NN models. The main purpose of this paper is to understand the mechanism of NN models by the approach of estimating training accuracy but not to analyze their generalization nor their performance in real-world applications. This study may provide a starting point for a new way for researchers to make progress on the difficult problem of understanding deep learning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Transformer Geometry Observatory TGO-III: Semantic Geometry Observatory

    cs.CV 2026-08 reject novelty 2.0 of 10

    Training a ViT-Small on ImageNet-100 makes class representations more linearly separable and globally separated while local class manifolds become more concentrated, but the evidence is descriptive and the hypothesis ...

Pith tools