Kick-Start your Understanding of Machine Learning with Python
summary
Shows building quick text pipelines with Python 3.6 using Scikit-learn for vectorization and k-means++ clustering and Keras on TensorFlow for supervision, demonstrating a working pipeline on Reuters (~22,000) articles. Converts sparse TF‑IDF outputs to dense matrices, removes stop words, writes intermediate feature matrices to Excel to inspect exact TF‑IDF numbers, and trains simple neural nets in under 20 lines. Notes tokenizer index effects, common-word misclassification, and recommends reducing problems to tiny examples before scaling and using TensorBoard for layer/weight diagnostics.
AI-written summary · about
chapters (11)
- 0:00Start
- 2:19PYTHON SET-UP
- 4:59TEXT CLASSIFICATION: PREPARATION
- 5:47DATA TO START WITH
- 8:14adding the CLUSTERING
- 9:07interpreting THE DATA
- 10:26CHECKING THE FEATURE MAP
- 16:20TOOLS & PRE-REQUISITES
- 18:17KERAS EXAMPLE
- 22:09understanding THE EXAMPLE OUTPUT
- 25:28understanding THE NETWORK
related talks
48mIntroduction to Natural Language Processing with Python
52mMachine Learning Data Pipelines
57mMachine Learning Data Pipelines
42mThe Machine Understands Text — Learning and Search at Micro and Macro Scale
44mTeaching Computers ABCs: A Quick Intro to Natural Language Processing
02h 19mWorkshop: Demystifying Natural Language Processing using Python (Scikit-Learn/ Keras)
01h 29mTricks, tips and topics in Text Analysis
01h 27mTips, Tricks and Topics in Text Analysis