Ian Goodfellow
Ian Goodfellow
collaborator
line weight = collaboration weight
Works in this corpus
| Title | Position | Year | Cited |
|---|---|---|---|
| Deep Learning | first | 2016 | 8,952 |
| Explaining and Harnessing Adversarial Examples | first | 2014 | 8,146 |
| Deep Learning with Differential Privacy | middle | 2016 | 6,220 |
| Intriguing properties of neural networks | middle | 2013 | 5,739 |
| Practical Black-Box Attacks against Machine Learning | middle | 2017 | 3,540 |
| Ensemble Adversarial Training: Attacks and Defenses | middle | 2017 | 1,861 |
| Adversarial Examples in the Physical World | middle | 2018 | 1,842 |
| Challenges in Representation Learning: A Report on Three Machine Learning Contests | first | 2013 | 1,588 |
| Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples | last | 2016 | 1,416 |
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.
- weakens4 distinct name form(s) across this row's works. Several unrelated spellings is the usual shape of two people sharing one record.
- supportsAt most 4 distinct institution(s) inside any five-year window, which is a normal career.
- supports96% of this row's works sit in its single largest field.
- neutralConfidence is judged on the 9 work(s) this corpus holds, not on the author's whole output. A single-work row carries little evidence either way.