How to Construct and Use Decision Trees
Description
Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence.
Join Jennifer Marsman as she welcomes Sonja Knoll to the show as they take a deep dive into Deep Learning as well as apply some real-world scenarios for you to try out on your own.
Looking for more information? Check out the following links below:
- Deep Learning – give it a try! Try the app http://CaptionBot.ai – works for any browser/phone
Call the Microsoft Cognitive Services API https://www.microsoft.com/cognitive-services
Build you own cool deep model on CNTK https://github.com/Microsoft/CNTK - Deep Learning
http://www.deeplearningbook.org - CNN
Generalization and Network Design Strategies by Lecun, Y., Technical Report CRG-TR-89-4, University of Toronto, 1989 - RNN
Learning representations by back-propagating errors by Rumelhart, D., Hinton, G., and Williams, R., Nature 323, 533–536, 1986 - Blog: The Unreasonable Effectiveness of Recurrent Neural Networks by Andrej Karpathy
- LSTM
Long Short-Term Memory by Hochreite, S., and Schmidhuber J., Neural Computation 9(8): 1735-1780, 1997
Blog: Understanding LSTM Networks by Christopher Olah
__________________________
__________________________
If you're interested in learning more about the products or solutions discussed in this episode, click on any of the below links for free, in-depth information:
Websites & Blogs:
Follow the conversation @MS_ITPro
Become a Fan @ facebook.com/MicrosoftITPro Subscribe to our podcast via iTunes, Stitcher, or RSS
Share
Download
Download this episode
- MP3 (38.3 MB)
- Low Quality MP4 (54.6 MB)
- High Quality MP4 (548.2 MB)
- Mid Quality MP4 (219.8 MB)
More episodes in this series
Startup Stories: An Interview with Olivier de Jong, Founder of Airwave
Related episodes
Behind the Scenes: How DroneWorks built a Safety Flight Platform for Industrial Drones…
Behind the Scenes: How Sensoria built a Smart, connected IoT golf grip with PGA Tour…
Behind the Scenes: How Zion China uses IoT and Machine Learning to evolve its Intelligent…
Behind the Scenes: Predicting the Early Onset of Brain Disease with BTT IoT Machine…
How to Construct and Use Decision Trees
Fun with Microsoft Cognitive Services
Startup Stories: An Interview with Sean Goltz and Addison Cameron-Huff from…
NASCAR & Microsoft: Driving Innovation Through Technology
How Azure ML Helped Predict the Results of the NCAA "March Madness" Tournament
Project: Fun with Mind Reading
The Discussion
-
ppolyzos The hyperlink tag for cognitive services is not closed properly, so the link is broken as it points to https://www.microsoft.com/cognitive-servicesBuild, which is not valid.
Correct link for Cognitive Services is https://www.microsoft.com/cognitive-services
-
gduncan411 @ppolyzos: Thanks for the heads-up... fixed
-
gduncan411 @ppolyzos: Thanks for the heads-up, it's been fixed
-
Jules Sorta awesome stuff.
Just a shame that the return to legacy neural networks methods, is such a slow learner technique, requiring powerful CPU, clouds for competitive deep machine learning. -
Tim have you tried to apply the word completion approach to number recognition? What would be the impact on the whole deep learning approach if the input data set is processed in real-time- the pixels of a picture for example are being introduced to the processor in random way?
-
Sonja Hi Tim - No, I haven’t tried that. To be clear, are you thinking of images as "sequences" of pixels? (similar to sequences of words for the word completion task). If that’s the case, I suppose one could use some sequence-related algorithms, like RNN/LSTM, but with two dimensions. Typically, CNNs are used for images since they encode the proximity of neighboring pixels. To your second point, one could submit the image to the model before it’s fully loaded, and get less-than-optimal results until the image is fully loaded.