Deep learning has generally been associated with unstructured data such as images, language, and audio. However it turns out that the structured data found in the columns of a database table or spreadsheet, where the columns can each represent different types of information in different ways (e.g. sales in dollars, area as zip code, product id, etc), can also be used very effectively by a neural network. This is equally true if the data can be represented as a time series (i.e. the rows represent different times or time periods). In particular, what we learnt in part 1 about embeddings can be used not just for collaborative filtering and word encodings, but also for arbitrary categorical variables representing products, places, channels, and so forth. This has been highlighted by the results of two Kaggle competitions that were won by teams using this approach. We will study both of these datasets and competition winning strategies in this lesson. Finally, we’ll look at how the Densenet architecture we studied in the last lesson can be used for image segmentation - that is, exactly specifying the location of every object in an image. This is another type of generative model, as we learnt in lesson 9, so many of the basic ideas from there will be equally applicable here. We hope you enjoyed your deep learning journey with us! Now that you’ve finished, be sure to drop by the forums to tell us how you’re using deep learning in your life or work, or what projects you’re considering working on now.
Views: 12373 Jeremy Howard
Describing the output of Decision tree and neural netwrok using SAS Enterprise Miner
Views: 3034 Nitin Paighowal
Instructure is a technology company committed to improving education. We provide instructors and students with modern tools and resources that empower and simplify the learning experience. Instructure offers Canvas, the open, easy-to-use, cloud-native learning management system, as well as Canvas Network, an index of open, online courses by educators everywhere — from Ivy League institutions to community colleges.
Views: 1307 CanvasLMS
Các thành viên Futurenet từ khắp nơi trên thế giới đã gặp nhau tại Macau vào ngày 9/9/2018 để kỷ niệm thành công của Futurenet và tìm hiểu về việc ra mắt sản phẩm mới của công ty và gặp một CEO mới. Một mối quan tâm lớn trong biến đổi khí hậu và sự tàn phá rừng đã mang FutureNet đến với Liên Hiệp Quốc. FutureNet hiện đang tung ra chương trình riêng của mình để bảo vệ các khu rừng.
Views: 597 FutureNet Viet Nam