Comments (2)
Hoping @okuchaiev and @borisgin can weigh in as well...
My understanding is that while numerous architectures were explored (different activation types, adding hidden layers, trying different numbers of nodes per layer, different dropout rates, different learning rates, dense re-feeding off and on, etc.), this confirmation had the best out-of-sample performance.
As to why this configuration performed the best in empirical experiments, I hypothesize that having a wide bottleneck layer helps the neural network learn a large number of "features" from the previous layer. Additionally, having a high dropout rate forces the model to learn robust features; e.g. with only 20% of the neurons active (80% dropout rate), the model must be extra careful when learning which features are most useful for the task at hand.
Thus, this configuration likely had the best out-of-sample performance because the wide bottleneck layer with the high dropout rate allowed the model to learn a large number of very robust features.
from deeprecommender.
Yes, I think @paulhendricks is right - wide middle layer with large dropout allows it to learn robust representations.
Regarding first layers (e.g. first encoder layer) and last layer (e.g. last decoder layer) - those are actually huge in terms of weights because number data (x) is high dimensional. This, if x is around 17,000 and first layer has only 128 activations, then it means that there are 17,000x128 weights in the first layer.
from deeprecommender.
Related Issues (20)
- Movielens experiments HOT 5
- Data issue
- tricks to reach 0.909? HOT 1
- Question about items not appearing in train set HOT 2
- Item Based CF
- netflix_data_convert script takes 88% system memory and become very slow afterwards HOT 1
- Add MovieLens example
- Deprecation warnings migrating to 0.4
- training on own data, and RMSE is nan HOT 2
- Implicit feedback HOT 3
- Question about dense re-feeding. HOT 3
- Your RMSE is too high,usually it is lower it betters
- How to get prediction from a model? HOT 1
- BUG: decode weight is not inited
- Expected range of labels
- Can I use this code for 0,1 rating data? HOT 1
- Top-N recommendation generation
- 'DataParallel' object has no attribute 'encode_w' HOT 2
- key error when loading the validation dataset HOT 2
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 deeprecommender.