Komputer mówi nie! Gartner ocenił, że w 2030 roku 85% projektów z AI będzie zwracało błędne wyniki. W swoim eseju napisałem dlaczego uważam, że jeszcze daleka droga zanim AI będzie w pełni używalne. Podałem też dlaczego ślepe zaufanie w sprawiedliwość algorytmu to droga donikąd.
W tym odcinku odpowiedzi na pytania: 💠 Czy developer C# potrzebuje Machine Learning? 💠 Czym jest uczenie maszynowe? 💠 Jaki problem rozwiązuje programista i ML Engineer (Data Scientist)? 💠 Jak wygląda proces ML? 💠 Czy Data Science to nadal egzotyczny zawód dla naukowców? 💠 Czym jest ML, a czym AI? 💠 Czy ML to tylko Python? 💠 Dlaczego Python jest tak popularny w Data Science? 💠 ML.NET - co jeśli cały stack technologiczny mam w .NET?
I will introduce you to how you can design a neural network in C# using TensorFlow.NET.
Transfer Learning is a popular tool in the field of Deep Learning. It is used to reuse a previously created model for a new problem. Thanks to that you can train neural networks with little data, which significantly saves time and memory resources required. This type of algorithm is also available in the ML.NET library. I want to show you its use on the example of Image Classification using a pre-trained TensorFlow model.
I wrote there about what this type of regression is and showed how it can be implemented in F # using the ML.NET library.
Today I will introduce you to the main problems and challenges of machine learning.
In the previous articles, we explored how we can use Microsoft’s new framework for machine learning – ML.NET. We used different datasets for different purposes and explored how to solve real-world problems. First, we used the Iris dataset to explore machine learning concepts and get up to speed with this field in general. This dataset is sort of Hello World example, but we wanted to learn how to deal with more ...
In the first article of machine learning in ML.NET saga, we explored basics of machine learning and we got our first look at Microsoft’s framework for this purpose. There we mentioned that machine learning addresses two kinds of problems: regression and classification. We used Iris classification dataset, which is sort of a Hello World! example in the machine learning world, in order to get familiar with the concepts...
Sztuka programowania 2318 dni, 14 godzin, 55 minut temu 25 źrodło rozwiń
In the previous article, we had a chance to look at the basics of machine learning and we got introduced to the way ML.NET framework is working. For that purpose, we have used Iris Dataset, which is a very basic classification problem. Let’s take up a notch and try to solve something which is a bit more advanced. In this article, we will see how we can apply same concepts from the previous article on one regression p...
Machine Learning is everywhere these days. I want to show how easy is to start your own journey with Azure Machine Learning.
Earlier this year I blogged about StockEstimator – my side project for predicting future stock prices. Recently in addition to F# module, which estimates future prices, I added Web Service that takes advantage of Azure Machine Learning to do the same much faster.
The era of big data is here and now. How to efficiently train support vector machines from massively large real-life datasets?
W tym tygodniu, który zaowocował wieloma nowościami, rozmawiam z Łukaszem Szulcem, który jest Microsoft Student Partnerem na Uniwersytecie Mikołaja Kopernika w Toruniu. Bardzo duża porcja nowości z zakresu HDInsight, Hadoop, Machine Learning, aplikacje mobilne i wiele, wiele innych. Zapraszam do oglądania! Share this:EmailFacebookTwitterLinkedInPosted on Author wisniaCategories Azure, Azure Backup, DocumentDB, HDInsight, Machine Learning, Mobile Engagement, Mobile Services, SQL DatabaseLeave a Reply Can...