|
|
|
|
LEADER |
02292nmm a2200301 u 4500 |
001 |
EB001910035 |
003 |
EBX01000000000000001072937 |
005 |
00000000000000.0 |
007 |
cr||||||||||||||||||||| |
008 |
210123 ||| eng |
100 |
1 |
|
|a Salon, Data
|
245 |
0 |
0 |
|a Automated Feature Engineering
|h [electronic resource]
|c Salon, Data
|
250 |
|
|
|a 1st edition
|
260 |
|
|
|b Data Science Salon
|c 2019
|
300 |
|
|
|a 1 video file, approximately 18 min.
|
653 |
|
|
|a Vidéo en continu
|
653 |
|
|
|a Vidéos sur Internet
|
653 |
|
|
|a Internet videos / http://id.loc.gov/authorities/subjects/sh2007001612
|
653 |
|
|
|a streaming video / aat
|
653 |
|
|
|a Streaming video / http://id.loc.gov/authorities/subjects/sh2005005237
|
041 |
0 |
7 |
|a eng
|2 ISO 639-2
|
989 |
|
|
|b OREILLY
|a O'Reilly
|
500 |
|
|
|a Mode of access: World Wide Web
|
500 |
|
|
|a Made available through: Safari, an O'Reilly Media Company
|
776 |
|
|
|z 0000000T91R98JO0
|
856 |
4 |
0 |
|u https://learning.oreilly.com/videos/~/00000OOT9LR98JO0/?ar
|x Verlag
|3 Volltext
|
082 |
0 |
|
|a E VIDEO
|
520 |
|
|
|a Presented by Namita Lokare Feature engineering plays a significant role in the success of a machine learning model. Most of the effort in training a model goes into data preparation and choosing the right representation. In this talk, I will focus on a robust feature engineering method, Randomized Union of Locally Linear Subspaces (RULLS). We generate sparse, non-negative, and rotation invariant features in an unsupervised fashion. RULLS aggregates features from a random union of subspaces by describing each point using globally chosen landmarks. These landmarks serve as anchor points for choosing subspaces. Our method provides a way to select features that are relevant in the neighborhood around these chosen landmarks. Distances from each data point to k closest landmarks are encoded in the feature matrix. The final feature representation is a union of features from all chosen subspaces. The effectiveness of our algorithm is shown on various real-world datasets for tasks such as clustering and classification of raw data and in the presence of noise. We compare our method with existing feature generation methods. Results show a high performance of our method on both classification and clustering tasks
|