thoughtworksinc / deepdarkfantasy Goto Github PK
View Code? Open in Web Editor NEWA Programming Language for Deep Learning
License: Apache License 2.0
deepdarkfantasy's People
Contributors
Stargazers
Watchers
Forkers
neutronest gitter-badger atry x1957 cloudfirst myhandson tifoit nillouise xstep coocoky frankszn jianweilin moyanzitto jshchengcong jinyu0310 z-shang dragoninstitute divinites silky zhangf911 freewen9292 jizhihang codeaudit youkilee cuijianzhu soledad89 strint hyiltiz aromazyl errord sexybear lejarx evan-zhao hades210 wenjinsun yatli dramforever semanticbeeng ur-me feibhwang hulalazz pstutz y-usuzumi occultism lfkdsk lazuraslong pinobox schliffendeepdarkfantasy's Issues
split SimpleLang
Add travis
Add shape
Add sigmoid
Add computable real
Let
make update curry
ai:Loss[A] cannot be implicitly converted to Loss.Aux[A, ai.loss]
Add Linear Type/Affine Type/other substructural logic
They dont need to respect abmonoid
Optimization, preferably using equality saturation: a new approach to optimization
convert *Lang to trait
loss of function is not really a monoid/abeilian monoid. Hide internal impl so it is.
Add Relu
Add n-dim array
not the same as List[List[x]](the latter does not require all elm to have same length)
Add Typeclass
add implicit def for impl of XXLang
rename Eval -> BEval
Backward mode ad
Some example will be nice
Add Fully Connected Layer
Split ShowLang
Add scan
Add Type Class: Numeric
Add issuestats.com
Add other form of automatic differentation
current form is exponentially slower (with problem on function)
Fold on List
Add Option
Move Lang to a seperate directory
Change Monoid to AbelianMonoid
Add Stream
Do some Semantic stuff
It will be good if we can find some rewrite rule that work under Eval (with backprop).
Possibly, we might want to prove backprop is the same for two program if it is the same under forward evaluation.
Move impl of EvalCase/LossCase into inner object of Eval impl
Add stuff in readme
Add visualization tool
more implicit info constructor
optimize with approximate computing
This is niubi， what is this for？
Can you add a Readme ？
Add Iterate
Split NextLang
rearrange argument in match
Generate AST for backward (so it can be optimized)
Fuzzy Logic
Add Boolean
First Class Paramteric Type
use https://github.com/adelbertc/tfm
Add CNN
First Class Type Constructor
Add automatic graident checking
First Class Dependent Type
Split type and value
Split and rename NaiveNextLang
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.