Cyrus Vahid
Employers on the program
- 2019–2022Amazon Web Services5 talks
Appearances by year
- AWS re:Invent
- PyData
Talks
| Date | Event | Conference | Role | Title | Links |
|---|---|---|---|---|---|
| Nov 28, 2022 | AWS re:Invent 2022 | AWS re:Invent | breakout | Explainable attention-based NLP using perturbation methods as AWS Explainable AI has gained a lot of attention from both legislators and the scientific community. There are many advantages of being able to explain the…Show lessExplainable AI has gained a lot of attention from both legislators and the scientific community. There are many advantages of being able to explain the reasoning behind the decisions a model makes, top among them are fairness, accountability, and causality. | SlidesVideo |
| Nov 28, 2022 | AWS re:Invent 2022 | AWS re:Invent | workshop | Using AutoML to develop deep learning solutions automatically as AWS Many companies, startups and enterprises alike, do not have the teams and processes needed to create their own research teams. The promise of AutoML is that it…Show lessMany companies, startups and enterprises alike, do not have the teams and processes needed to create their own research teams. The promise of AutoML is that it allows companies and scientists to create deep learning solutions without possessing a deep knowledge of deep learning. | Slides |
| Dec 12, 2019 | PyData Warsaw 2019 | PyData | talk | Anyone can Build Great Deep Learning Applications - Deep Numpy as Amazon AI As deep learning becoming prevalent in adoption of practical AI, it is important to lower barrier to entry for DL adoption for the developer community. | |
| Dec 2, 2019 | AWS re:Invent 2019 | AWS re:Invent | builders session | [REPEAT 2] Amazon SageMaker: Automatically tune hyperparameters as Amazon Web Services – AWS Deep Engine Amazon SageMaker offers automatic model tuning so you can use machine learning to quickly tune your model to be as accurate as possible. This capability lets…Show lessAmazon SageMaker offers automatic model tuning so you can use machine learning to quickly tune your model to be as accurate as possible. This capability lets you skip the tedious trial-and-error process of manually adjusting model parameters. | Slides |
| Dec 2, 2019 | AWS re:Invent 2019 | AWS re:Invent | chalk talk | Build accurate models with automatic model tuning as Amazon Web Services In many cases, what separates good models from great ones is the choice of hyperparameters. For example, how many layers you should use? | Slides |
Frequent co-speakers
| Speaker | Shared events | Shared talks | Last together |
|---|---|---|---|
| Aaron Friedman | 2 | — | 2022 |
| Aaron Khoo | 2 | — | 2022 |
| Aaron Rallo | 2 | — | 2022 |
| Aashmeet Kalra | 2 | — | 2022 |
| Adam Wagner | 2 | — | 2022 |
| Aditya Bindal | 2 | — | 2022 |
| Aditya Krishnan | 2 | — | 2022 |
| Ahmed Omran | 2 | — | 2022 |
| Ajit Rajdeosingh | 2 | — | 2022 |
| Akash Jain | 2 | — | 2022 |
| Alan Halachmi | 2 | — | 2022 |
| Alex Bestavros | 2 | — | 2022 |
| Alex Burkleaux | 2 | — | 2022 |
| Alex DeBrie | 2 | — | 2022 |
| Ali Saidi | 2 | — | 2022 |
Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.