To wydarzenie już się odbyło. Sprawdź nadchodzące wydarzenia
KMD Meetup on Machine Learning
Wydarzenie:
KMD Meetup on Machine Learning
Typ wydarzenia:
Spotkanie
Kategoria:
Tematyka:
Data:
28.11.2018 (środa)
Godzina:
18:00
Język:
angielski
Wstęp:
Bezpłatne
Miasto:
Miejsce:
KMD Poland office
Adres:
Inflancka 4A, building A
Zaloguj się, by zgłosić zmianę.
Opis:
What neural networks can (and cannot yet) do?
Deep learning (artificial neural networks) is progressing at a rapid pace. In the last few years image recognition performance went from not useful to on a par with human level. Lately, AlphaGo Zero not only beat human masters, but was able to do so entirely learning by playing with itself. And it keeps going; something that was an original discovery 6 months ago may have become an industry baseline
Moreover, it is relatively easy to start using deep learning - using Python libraries such as Keras or PyTorch. So - should you use it in your project? Is it going to work at all? And if so - is it worth your effort?
I will talk about which problems are likely to be solved by Deep Learning – the kinds of problems, amount of data needed and expected accuracy.
I will show which kind of problems are as easy as using some existing API or "import some_library", which require some work and experience, and which are still out of reach.
I will focus on computer vision, but add a few examples of natural language processing.
Deep learning (artificial neural networks) is progressing at a rapid pace. In the last few years image recognition performance went from not useful to on a par with human level. Lately, AlphaGo Zero not only beat human masters, but was able to do so entirely learning by playing with itself. And it keeps going; something that was an original discovery 6 months ago may have become an industry baseline
Moreover, it is relatively easy to start using deep learning - using Python libraries such as Keras or PyTorch. So - should you use it in your project? Is it going to work at all? And if so - is it worth your effort?
I will talk about which problems are likely to be solved by Deep Learning – the kinds of problems, amount of data needed and expected accuracy.
I will show which kind of problems are as easy as using some existing API or "import some_library", which require some work and experience, and which are still out of reach.
I will focus on computer vision, but add a few examples of natural language processing.
Uczestnicy (1):