Andrew Y. Ng
Andrew Y. Ng
collaborator
line weight = collaboration weight
Works in this corpus
| Title | Position | Year | Cited |
|---|---|---|---|
| Latent dirichlet allocation | middle | 2003 | 27,078 |
| Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank | middle | 2013 | 6,849 |
| Learning Word Vectors for Sentiment Analysis | middle | 2011 | 3,294 |
| Apprenticeship learning via inverse reinforcement learning | last | 2004 | 2,895 |
| Distance Metric Learning with Application to Clustering with Side-Information | last | 2002 | 2,703 |
| Cheap and fast---but is it good? | last | 2008 | 1,928 |
| On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes | first | 2001 | 1,888 |
| Reasoning With Neural Tensor Networks for Knowledge Base Completion | last | 2013 | 1,665 |
| Feature selection, L 1 vs. L 2 regularization, and rotational invariance | first | 2004 | 1,603 |
| Deep Speech: Scaling up end-to-end speech recognition | last | 2014 | 1,519 |
Is this one person?
This record is probably one person, but at least one signal is weak. Check the evidence below before relying on the totals.
- supportsAn ORCID is claimed by a person, not inferred, so it is the only identity assertion here that a human made.
- weakens3 distinct name form(s) across this row's works. Several unrelated spellings is the usual shape of two people sharing one record.
- supportsAt most 2 distinct institution(s) inside any five-year window, which is a normal career.
- supports90% of this row's works sit in its single largest field.
- neutralConfidence is judged on the 10 work(s) this corpus holds, not on the author's whole output. A single-work row carries little evidence either way.