Videos

Use Cases – Ep. 12 (Deep Learning SIMPLIFIED)



DeepLearning.TV

Despite its popularity, machine vision is not the only Deep Learning application. Deep nets have started to take over text processing as well, beating every traditional method in terms of accuracy. They also are used extensively for cancer detection and medical imaging. When a data set has highly complex patterns, deep nets tend to be the optimal choice of model.

Demo URLs
Clarifai – http://www.clarifai.com
Metamind – https://www.metamind.io/language/twitter

As we have previously discussed, Deep Learning is used in many areas of machine vision. Facebook uses deep nets to detect faces from different angles, and the startup Clarifai uses these nets for object recognition. Other applications include scene parsing and vehicular vision for driverless cars.

Deep Learning TV on
Facebook: https://www.facebook.com/DeepLearningTV/
Twitter: https://twitter.com/deeplearningtv

Deep Nets are also starting to beat out other models in certain Natural Language Processing tasks like sentiment analysis, which can be seen with new tools like MetaMind. Recurrent nets can be used effectively in document classification and character-level text processing.

Deep Nets are even being used in the medical space. A Stanford team was able to use deep nets to identify 6,642 factors that help doctors better predict the chances of cancer survival. Researchers from IDSIA in Switzerland used a deep net to identify invasive breast cancer cells. In drug discovery, Merck hosted a deep learning challenge to predict the biological activity of molecules based on chemical structure.

In finance, deep nets are trained to make predictions based on market data streams, portfolio allocations, and risk profiles. In digital advertising, these nets are used to optimize the use of screen space, and to cluster users in order to offer personal ads. They are even used to detect fraud in real time, and to segment customers for upselling/cross-selling in a sales environment.

What is your favorite deep learning application? Please comment and share your thoughts.

Credits
Nickey Pickorita (YouTube art) –
https://www.upwork.com/freelancers/~0147b8991909b20fca
Isabel Descutner (Voice) –
https://www.youtube.com/user/IsabelDescutner
Dan Partynski (Copy Editing) –
https://www.linkedin.com/in/danielpartynski
Marek Scibior (Prezi creator, Illustrator) –
http://brawuroweprezentacje.pl/
Jagannath Rajagopal (Creator, Producer and Director) –
https://ca.linkedin.com/in/jagannathrajagopal

Source

Similar Posts

31 thoughts on “Use Cases – Ep. 12 (Deep Learning SIMPLIFIED)
  1. Hi DeepLearning TV. Your videos are awesome,
    could you maybe add some videos on machine translation, how to integrate context information of an sentence in an neural network

  2. survival prediction, pathogen discovery, drug interaction, genetic viability, genetic mutability, chemical property prediction, chemical combination and environment requirement prediction, and agricultural geographic condition tracking.

    anything financial seems a little bit like mongering

  3. Finance is the most interesting for me. I'm thinking about developing a deep net model to predict values in a time series with data extracted from FOREX market. Do you think a could use a recurrent neural net for that? Let me know.

  4. Hi and sorry for my ignorance about technology but what is the actual improvement between Akhinator and other current use cases of Deep learning? Akhinator also recognizes patterns right? Is is about the number of inputs that a deep net is able to "proceed" or about the number of classifiers?

    Idk anything about technology, doing some research as part of an environmental scanning (PESTE model) for school.

    Thank you

  5. Your videos are really good. Really good. But maybe try to avoid trivial explanations such as "clicking on a button on a web page to upload an image". (We can probably assume that the target audience is proficient enough in general computer usage.)

  6. Great videos, I really appreciate them! Have you considered to make a video for non-technical people? We are surrounded with neural network-based solutions, a brief and light summary might be interesting for a broader audience.

  7. I actually love your videos. I recently got an internship position as a research assistance for my university professor and it will be about using CNN in processing of ultrasound images of heart. I had no experience or knowledge of machine learning. I started with your videos and I am still keep watching them. Need to watch all of it 🙂

  8. Thank you so much for such amazing videos, can you please elaborate more on the applications of Finance and in particular short time stock market prediction. In particular my question is which deep learning method is suitable for short time trading ? if you can give me your opinion or refer to a paper or something I can explore that would be really amazing thanks

  9. One of the best series for Deep Learning Starter.I would surely recommend it to beginners to watch it at least once. Also, Clarifyai has changed their demo with defaults images and video available. and I think, that is even cooler than the old demo.
    Please check URL for MetaMind. I guess, its broken.

  10. Great stuff ! I'm an experienced trader and algo trader but never before with ML. Would you have any recommendations regarding 'hands on' ML n security trading ?

Comments are closed.

WP2Social Auto Publish Powered By : XYZScripts.com