Both sides previous revisionPrevious revisionNext revision | Previous revisionNext revisionBoth sides next revision |
pub:teaching:courses:rnd [2018/05/30 10:05] – [2018-04-25] sbk | pub:teaching:courses:rnd [2018/05/30 10:10] – [2018-04-25] sbk |
---|
- 2018-03-28 [[pub:teaching:courses:rnd#section20180328|Richard Lucas]] TedxKazimierz | - 2018-03-28 [[pub:teaching:courses:rnd#section20180328|Richard Lucas]] TedxKazimierz |
- 2018-04-25 [[pub:teaching:courses:rnd#section20180425|SKK S.A. - IoT i sztuczna inteligencja – jak poskromić technologię]] | - 2018-04-25 [[pub:teaching:courses:rnd#section20180425|SKK S.A. - IoT i sztuczna inteligencja – jak poskromić technologię]] |
- 2018-06-06 [[pub:teaching:courses:rnd#section20180606|Philip Morris INternational - Artificial Intelligence at PMI - Automating Business Processes in a Corporate Environmen]] | - 2018-06-06 [[pub:teaching:courses:rnd#section20180606|Philip Morris International - Artificial Intelligence at PMI - Automating Business Processes in a Corporate Environment]] |
| |
==== Jesień 2017 - dodatkowe spotkania ==== | ==== Jesień 2017 - dodatkowe spotkania ==== |
| |
===== Spotkania RnD 2018 ===== | ===== Spotkania RnD 2018 ===== |
==== 2018-04-25 ==== | ==== 2018-06-06 ==== |
<WRAP column 15%> | <WRAP column 15%> |
{{:pub:teaching:courses:rnd2018-06-06.png?200|}} | {{:pub:teaching:courses:rnd2018-06-06.png?200|}} |
| |
<WRAP column 75%> | <WRAP column 75%> |
{{ :pub:teaching:courses:augustyn_lorenc.jpg?nolink&100|}} | |
**Gość**: Augustyn Lorenc – specjalista ds. badań i rozwoju | {{ :pub:teaching:courses:pmi_logo.jpg?600 |}} |
| |
**Temat**: | **Temat**: |
| |
**Contents:** | **Contents:** |
- Team Introduction | - **Team Introduction** |
- Experiment #1 - 'Deep Learning based Natural Language Search' \\ In this talk, we will provide details of a Deep Learning based solution (DrQA) for Natural Language Search over factory machine manuals. The proposed architecture allows identifying the precise answer span corresponding to a query, which improves over the paragraph level answers enabled by pure statistical approaches. | - **Experiment #1 - 'Deep Learning based Natural Language Search'** \\ In this talk, we will provide details of a Deep Learning based solution (DrQA) for Natural Language Search over factory machine manuals. The proposed architecture allows identifying the precise answer span corresponding to a query, which improves over the paragraph level answers enabled by pure statistical approaches. |
- Experiment #2 - 'Planogram - Shelf Compliance at Point of Sale' \\ In this talk we will provide details of a Deep Learning based solution for shelf compliance image recognition use-case at PMI Points-of-Sales (PoS). The experimental architecture consists of two stages, first one detects all positions on the shelf (empty positions, our and non PMI products). The second one is executing classification of detected positions and provides a type of each. System finds all PMI products and their types, non-PMI products, empty slots, counts them and verifies if everything is placed correctly due to PMI requirements. | - **Experiment #2 - 'Planogram - Shelf Compliance at Point of Sale'** \\ In this talk we will provide details of a Deep Learning based solution for shelf compliance image recognition use-case at PMI Points-of-Sales (PoS). The experimental architecture consists of two stages, first one detects all positions on the shelf (empty positions, our and non PMI products). The second one is executing classification of detected positions and provides a type of each. System finds all PMI products and their types, non-PMI products, empty slots, counts them and verifies if everything is placed correctly due to PMI requirements. |
- Experiment #3 - 'Helpdesk Ticket Classification' \\ In this talk we will provide details about neural network based solution for helpdesk ticket classification. The experimental network architecture consists of a mix of fully connected layers on top of number of keyword occurrences and a stack of one dimensional convolutions over word vector embeddings for the whole text. | - **Experiment #3 - 'Helpdesk Ticket Classification'** \\ In this talk we will provide details about neural network based solution for helpdesk ticket classification. The experimental network architecture consists of a mix of fully connected layers on top of number of keyword occurrences and a stack of one dimensional convolutions over word vector embeddings for the whole text. |
- Discussion & Closing | - **Discussion & Closing** |
| |
**Speakers’ Biograms** | **Speakers’ Biograms** |
| |
**About PMI** | **About PMI** |
| |
Philip Morris International is a leading international tobacco company, with a diverse workforce of around 81,000 people. Our products are the choice of 150 million consumers worldwide, and for those who choose to continue to smoke, we will continue to offer them the best quality products. But that’s not where our vision for smokers ends. | Philip Morris International is a leading international tobacco company, with a diverse workforce of around 81,000 people. Our products are the choice of 150 million consumers worldwide, and for those who choose to continue to smoke, we will continue to offer them the best quality products. But that’s not where our vision for smokers ends. |
We’re dedicated to doing something very dramatic – replacing cigarettes with the smoke-free products that we’re developing and selling. That’s why we have a total of over 400 dedicated scientists, engineers, and technicians developing less harmful alternatives to cigarettes at our two Research & Development sites in Switzerland and Singapore. It’s the biggest shift in our history. | We’re dedicated to doing something very dramatic – replacing cigarettes with the smoke-free products that we’re developing and selling. That’s why we have a total of over 400 dedicated scientists, engineers, and technicians developing less harmful alternatives to cigarettes at our two Research & Development sites in Switzerland and Singapore. It’s the biggest shift in our history. |
| |
Further information: | Further information: |
[[www.pmi.com]] | * [[http://www.pmi.com|]] |
[[www.pmiscience.com]] | * [[http://www.pmiscience.com|]] |
[[www.pmicareers.com]] | * [[http://www.pmicareers.com|]] |
| |
</WRAP> | </WRAP> |