# Modelling the influence of data structure on learning in neural networks

@article{Goldt2019ModellingTI, title={Modelling the influence of data structure on learning in neural networks}, author={Sebastian Goldt and Marc M{\'e}zard and Florent Krzakala and Lenka Zdeborov{\'a}}, journal={ArXiv}, year={2019}, volume={abs/1909.11500} }

The lack of crisp mathematical models that capture the structure of real-world data sets is a major obstacle to the detailed theoretical understanding of deep neural networks. Here, we first demonstrate the effect of structured data sets by experimentally comparing the dynamics and the performance of two-layer networks trained on two different data sets: (i) an unstructured synthetic data set containing random i.i.d. inputs, and (ii) a simple canonical data set containing MNIST images. Our… CONTINUE READING

#### Citations

##### Publications citing this paper.

## Hidden Unit Specialization in Layered Neural Networks: ReLU vs. Sigmoidal Activation

VIEW 1 EXCERPT

CITES BACKGROUND

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 37 REFERENCES

## Three unfinished works on the optimal storage capacity of networks

VIEW 4 EXCERPTS

HIGHLY INFLUENTIAL

## Statistical Mechanics of Learning

VIEW 4 EXCERPTS

HIGHLY INFLUENTIAL

## Counting the learnable functions of structured data

VIEW 1 EXCERPT

## and M

VIEW 1 EXCERPT

## Daniel D

VIEW 1 EXCERPT