Comments (7)
I feel in deep learningl we should cover 5 topics and give each topic two weeks .
For eg: if one topic is introduction to neural networks , in which we cover what they are, how to lay the basic structure in tf, activation functions , loss functions , etc. We can distribute this in two weeks.
We can make one topic be NLP in this. This will acct for 10 weeks
This will give us 4 weeks for projects , in which we can cover projects like recommendation sys. If we want to give one week to each project then we will have to look for four projects.
from ml-track.
@tarushi98 @l-ightmare @radioactive11 @subhankar01 @Ramitphi
Please discuss the curriculum.
from ml-track.
@tarushi98 Please give a detail of weeks like
- Week 9:
- Week 10:
Like that
from ml-track.
@kabirnagpal @radioactive11 @subhankar01 @Ramitphi @l-ightmare
Kabir , discussed an idea for the Deep Learning track. Check it out and let's discuss what all can be added.
We have thought of covering it this way:
- Explaining few basics by coding the Dog Cat classifier in either Keras or fastai or both
2)Discussing preprocessing methods for NLP and implementing one Application. - One implementation each of LSTM and RNN.
These all can be covered for 2 weeks each.
@kabirnagpal If I forgot something, please add.
from ml-track.
- Week 9: NLP processing methods
- Week 10: Deep Learning ( explanation of concepts using a simple classifier in Keras or FastAI )
- Week 11: NLP using Deep Learning ( intro to RNN )
Please reply here on the thread and recommend ideas and changes
@tarushi98 @radioactive11 @subhankar01 @l-ightmare @Ramitphi
from ml-track.
from ml-track.
- week 9: Open CV and Yolo @l-ightmare @radioactive11
- week 10: MNIST, Cat Dog @charansoneji @subhankar01 @Ramitphi
- week 11: Transfer Learning, RNN: COVID @tarushi98 @kabirnagpal
- Week 12: NLP: preprocessing, glove, summarisation
- week 13: Embedding layers, FASTAI, Bert: optional
- week 14: Gans
- week 15: deployment: fast API
Project: Face recognition, Recommendation systems, Neural Style
@tarushi98 @radioactive11 @subhankar01 @Ramitphi @charansoneji @l-ightmare
from ml-track.
Related Issues (3)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ml-track.