|
|
|
|
| LEADER |
02389nmm a2200397 u 4500 |
| 001 |
EB001921612 |
| 003 |
EBX01000000000000001084514 |
| 005 |
00000000000000.0 |
| 007 |
cr||||||||||||||||||||| |
| 008 |
210123 ||| eng |
| 050 |
|
4 |
|a QA76.9.A25
|
| 100 |
1 |
|
|a Vagata, Pamela
|
| 245 |
0 |
0 |
|a Fraud detection without feature engineering
|c Pamela Vagata
|
| 260 |
|
|
|a [Place of publication not identified]
|b O'Reilly
|c 2019
|
| 300 |
|
|
|a 1 streaming video file (40 min., 11 sec.)
|
| 653 |
|
|
|a Sécurité informatique
|
| 653 |
|
|
|a Machine learning / http://id.loc.gov/authorities/subjects/sh85079324
|
| 653 |
|
|
|a Computer networks / Security measures / http://id.loc.gov/authorities/subjects/sh94001277
|
| 653 |
|
|
|a Criminalité informatique / Enquêtes
|
| 653 |
|
|
|a Computer networks / Security measures / fast / (OCoLC)fst00872341
|
| 653 |
|
|
|a Apprentissage automatique
|
| 653 |
|
|
|a Computer security / fast / (OCoLC)fst00872484
|
| 653 |
|
|
|a Réseaux d'ordinateurs / Sécurité / Mesures
|
| 653 |
|
|
|a Computer security / http://id.loc.gov/authorities/subjects/sh90001862
|
| 653 |
|
|
|a Computer crimes / Investigation / http://id.loc.gov/authorities/subjects/sh85029493
|
| 653 |
|
|
|a Computer Security
|
| 653 |
|
|
|a Machine learning / fast / (OCoLC)fst01004795
|
| 653 |
|
|
|a Computer crimes / Investigation / fast / (OCoLC)fst00872065
|
| 041 |
0 |
7 |
|a eng
|2 ISO 639-2
|
| 989 |
|
|
|b OREILLY
|a O'Reilly
|
| 500 |
|
|
|a Title from title screen (viewed November 14, 2019). - Recorded at the 2019 O'Reilly Artificial Intelligence Conference in New York
|
| 856 |
4 |
0 |
|u https://learning.oreilly.com/videos/~/0636920339540/?ar
|x Verlag
|3 Volltext
|
| 082 |
0 |
|
|a 331
|
| 082 |
0 |
|
|a 000
|
| 082 |
0 |
|
|a 364.1
|
| 520 |
|
|
|a "Pamela Vagata (Stripe) explains how Stripe has applied deep learning techniques to predict fraud from raw behavioral data. Since fraud detection is a critical business problem for Stripe, the company already had a well-tuned feature-engineered model for comparison. Stripe found that the deep learning model outperforms the feature-engineered model both on predictive performance and in the effort spent on data engineering, model construction, tuning, and maintenance. Join in to discover how common industry practice could shift toward deeper models trained end to end and away from labor-intensive feature engineering."--Resource description page
|