Understanding deep learning

By Christian Reimers. 2023

138 citations recorded by the source corpus.

Subfields: Scaling & Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Scaling & Learning Theory

1. Dacheng Tao
2. Kyunghyun Cho
3. Samuel R. Bowman
4. Fengxiang He
5. Masashi Sugiyama
6. Issei Sato

Citations in the corpus

• Comparing Test Sets with Item Response Theory (2021, methodology): “Unlike previous work which focuses on example-level analysis within individual datasets (Lalor et al., 2016, 2018), here we analyze example characteristics from a larger perspective by comparing individual examples across datasets.”
• Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting (2020, background): “Besides, former empirical results demonstrate that deep neural networks almost surely achieve zero training error even when the training data is randomly labelled (Zhang et al., 2017).”