Differences

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

--- ml:ml_overview [2022/05/15 01:06] – jmflanig
+++ ml:ml_overview [2024/11/27 21:56] (current) – [Machine Learning Overview] jmflanig
@@ Line 3: / Line 3: @@
 This is a resource to help you get up to speed in various topics if you're trying to learn ML on your own or broaden your ML knowledge.
+See also [[https://aman.ai/primers/ai/|Aman.ai - AI Fundamentals]]
 ===== Books =====
   * Pattern Recognition and Machine Learning, Bishop, 2006 (Referenced below as Bishop) available [[https://www.microsoft.com/en-us/research/uploads/prod/2006/01/Bishop-Pattern-Recognition-and-Machine-Learning-2006.pdf|here]] or [[https://jlab.soe.ucsc.edu/nlp-wiki/lib/exe/fetch.php?media=book:bishop.pdf|local copy]]
@@ Line 15: / Line 17: @@
   * [[https://www.jair.org/index.php/jair/article/view/11030|A Primer on Neural Network Models for Natural Language Processing, Yoav Goldberg, 2016]] [[https://jlab.soe.ucsc.edu/nlp-wiki/lib/exe/fetch.php?media=book:nn_primer.pdf|local copy]] (Referenced below as NNPrimer)
   * The Matrix Cookbook, available [[https://svivek.com/teaching/deep-learning-nlp/spring2019/resources/matrixcookbook.pdf|here]]
+  * [[https://www.eleuther.ai/beginners.pdf|Intro to ML]] (note this was released April 1st)
 ===== Courses =====
   * [[https://www.cs.cornell.edu/courses/cs4780/2018fa/lectures/|Machine Learning for Intelligent Systems @ Cornell]]
+  * Very quick intro to machine learning (slides): [[https://indico.physics.lbl.gov/event/569/contributions/1382/attachments/1268/1407/gs-20170913.pdf|Introduction to Machine Learning]] {{papers:quick-ml-intro.pdf|local copy}}
 ===== Overview of Topics =====
@@ Line 79: / Line 83: @@
       * **Tests of Significance** [[http://ciml.info/dl/v0_99/ciml-v0_99-all.pdf#page=67|CIML p. 67-69]]
     * **Data Resampling Methods**
-      * **k-fold Cross Validation** Be careful using this method on NLP datasets! Due to the non-IID nature of NLP datasets, it is generally not recommended to use k-fold cross validation (can over-estimate performance).
+      * **k-fold Cross Validation** Be careful using this method on NLP datasets! Due to the non-IID nature of NLP datasets, it is generally not recommended to use k-fold cross validation (can over-estimate performance).  Better to use a thoughtfully-chosen train/dev/test split.
       * ** *Bootstrap Resampling**
       * **Jacknife**
@@ Line 166: / Line 170: @@
     * **SpaCy**
     * **OpenCV**
+===== Related Pages =====
+  * [[Deep Learning]]
+  * [[ML Glossary]] (glossary of slightly more advanced terms)