This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
:smile: |
- Python: https://docs.python-guide.org/#writing-great-python-code
- ReactJS: Take the tutorials at https://reactjs.org/ and make sure you understand the concepts. Reach out if you have any questions.
- NodeJS: https://nodejs.org/en/. We use it for REST APIs. A basic understanding will be good.
- Docker: All services are containerized.
- Kubernetes: We plan to move services to K8.
- Google Cloud Platform: Get a good understanding of different services and focus on pub-sub, IOT Core, Dataflow, GCE, GAE, Cloud SQL, BigQuery, GKE, etc.
- RESTful APIs: https://en.wikipedia.org/wiki/Representational_state_transfer and https://restfulapi.net/.
- Redis: https://redis.io/
-
Emotional intelligence
- Ability to read and understand emotions -- Affectiva uses emotions on face, i.e. facial features.
-
Color Images representation
- Depth is the number of channels
If the identification problem is easier in color for us humans, it’s likely easier for an algorithm to see color images too!
https://www.youtube.com/watch?v=F5mRW0jo-U4
- python manage.py runserver
SECRET_KEY
andDEBUG
modeINSTALLED_APPS
(basically components of the Django project)
- Lobster-human analogy
- Try to wake up at same time everyday- fat and protein heavy breakfast
- Feedback Loop - if you look defeated, people will look at you that way; if you straighten up, people will look at you differently
So, attend carefully to your posture. Quit drooping and hunching around. Put your desires forward, as if you had a right to them- at least the same right as others. Walk tall and gaze forthrightly ahead. Dare to be dangerous.
-
What is an autoencoder?
- Makes a compressed representation of a data without any human intervention
- Cons Bad compression and generalizing to datasets
- Pros Dimensionality Reduction and Image denoising
-
A simple autoencoder
- Just compresses data, for example images from the MNIST database.