Completed
ABOUT BASIS TECHNOLOGY
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Understanding Names with Neural Networks - Session 2
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 ABOUT BASIS TECHNOLOGY
- 3 Rosette Capabilities
- 4 Names are a Challenge
- 5 Task: Name Matching
- 6 Name Matching Algorithms
- 7 Step One: Modeling Sequences of Characters
- 8 Step Two: Modeling Transliterations
- 9 Issues with HMM-Based Name Matching
- 10 What does an HMM Actually Do?
- 11 How Would You Transliterate a Name?
- 12 The Antidote: Sequence-to-Sequence (seq2seq)
- 13 Neural Network of Choice: Long Short-Term Memory (LSTM) Cells
- 14 Step One: Learning to Transliterate with seq2seq
- 15 Step Two: Running the Transliterator in Reverse to Score
- 16 How Can We Produce a Score?
- 17 Processing Time on Name Pairs (seconds)
- 18 Faster seq2seq with a Convolutional Neural Network CNNO
- 19 Convolutional Neural Net (CNN)
- 20 CNN in Natural Language Processing
- 21 What Does This Tell Us?
