Differences

This shows you the differences between two versions of the page.

--- ml:neural_network_psychology [2021/03/06 09:01] – created jmflanig
+++ ml:neural_network_psychology [2025/03/27 00:33] (current) – [Related Pages] jmflanig
@@ Line 1: / Line 1: @@
 ====== Neural Network Psychology ======
-"Neural network psychology" is a term Kevin Knight uses to refer to the study of how neural networks learn and why they make the predictions they do.  See below for examples.
+"Neural network psychology" is the study of what neural networks learn and why they make the predictions they do.  See below for examples.
 ===== Papers =====
   * [[https://www.aclweb.org/anthology/D16-1248.pdf|Shi et al 2016 - Why Neural Translations are the Right Length]]
-  * [[https://www.isi.edu/natural-language/mt/emnlp16-nmt-grammar.pdf|Shi et al 2016 - Does String-Based Neural MT Learn Source Syntax?]]
+  * [[https://www.aclweb.org/anthology/D16-1159.pdf|Shi et al 2016 - Does String-Based Neural MT Learn Source Syntax?]]
+  * [[http://www.mitpressjournals.org/doi/pdfplus/10.1162/tacl_a_00115|Linzen et al 2016 - Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies]]
+  * [[https://arxiv.org/pdf/1905.06316.pdf|Tenney et al 2019 - What do you learn from context? Probing for sentence structure in contextualized word representations]] Introduces the technique of "edge probing"
+  * [[https://arxiv.org/pdf/1905.05950.pdf|Tenney et al 2019 - BERT Rediscovers the Classical NLP Pipeline]] Uses "edge probing"
+  * [[https://www.aclweb.org/anthology/P19-1356.pdf|Jawahar et al 2019 - What does BERT learn about the structure of language?]]
+  * [[https://helda.helsinki.fi/bitstream/handle/10138/263704/W18_5431_1.pdf?sequence=1|Raganato et al 2018 - An Analysis of Encoder Representations in Transformer-Based Machine Translation]]
+  * [[https://arxiv.org/pdf/2310.03686|Langedijk et al 2023 - DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers]]
+===== Notes =====
+  * I believe Kevin Knight came up with this term
+===== Workshops =====
+  * [[https://blackboxnlp.github.io/|BlackboxNLP]]
+===== Related Pages =====
+  * [[nlp:Bert and Friends#Interpretation Bertology|BERTology]]
+  * [[nlp:Explainability]]
+  * [[ml:Mechanistic Interpretability]]
+  * [[nlp:Probing Experiments]]