Comments (2)
From Backprop as Functor (Fong, Spivak, Tuyeras):
In this paper we will show that learning becomes compositional — i.e. we can define a learning algorithm
A → C
from learning algorithmsA → B
andB → C
— as long as each learning algorithm consists of these four components:
- a parameter space
P
,- a function
I : P × A → B
,- an update function
U : P × A × B → P
, and- a request function
r : P × A × B → A
[...]
Namely, we will show that
Learn
has the structure of a symmetric monoidal category.
This would be a good way to abstract out the NN
package without committing to a backend for auto differentiation as Torch (also backprop) provide us with functions that resemble this.
from hasktorch.
closing for the time being
from hasktorch.
Related Issues (20)
- Nix instructions do not build HOT 3
- dlopen: symbol not found in flat namespace '__ZN2at13globalContextEv' HOT 1
- Dockerfile raises error HOT 2
- test
- test
- Shape checking skipped when output shape is not specified
- Compilation error about dependencies when trying to build.
- Library won't compile. HOT 1
- Docker doesn't build normally. HOT 1
- How can I use hasktorch as a library through haskell.nix? HOT 5
- GHC-9.6.2 support HOT 1
- Running stack ghci on hasktorch directory gives an error. HOT 3
- Build failure with GHC 9.4.7 (Stack LTS 21.15) HOT 3
- Building with cabal chokes on a commit sha from cabal.project HOT 3
- CI: reducing cache sizes to better cope with the 10 GB limit HOT 2
- Compiling on windows HOT 2
- libnvrtc-builtins.so.11.3 can't be found
- `cabal repl hasktorch` does nothing
- Plans / roadmap to release v0.2 ? HOT 11
- Not being able to move MutableTensor to GPU HOT 1
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 hasktorch.