L1: Tensor Studio - a more practical continuation of the ideas presented in Moniel.

Human-friendly declarative dataflow notation for computational graphs. See video.

Moniel.dmg (77MB)

Moniel is one of many attempts at creating a notation for deep learning models leveraging graph thinking. Instead of defining computation as list of formulea, we define the model as a declarative dataflow graph. It is not a programming language, just a convenient notation. (Which will be executable. Wanna help?)

Note: Proper syntax highlighting is not available here on GitHub. Use the application for the best experience.

Let's start with nothing, i.e. comments:

Node can be created by stating its type:

You don't have to write full name of a type. Use acronym that fits you! These are all equivalent:

Nodes connect with other nodes with an arrow:

There can be chain of any length:

Also, there can be multiple chains:

Nodes can have identifiers:

Identifiers let's you refer to nodes that are used more than once:

However, this can be rewritten without identifiers using list:

Lists let's you easily declare multi-connection:

List-to-list connections are sometimes really handy:

Nodes can take named attributes that modify their behavior:

Attribute names can also be shortened:

Defining large graphs without proper structuring is unmanageable. Metanodes can help:

Metanodes are more powerful when they define proper Input-Output boundary:

Alternatively, you can use inline metanodes:

Or you don't need to give it a name:

If metanodes have identical structure, we can create a reusable metanode and use it as a normal node:

• Piotr Migdal: Simple Diagrams of Convoluted Neural Networks - great summary on visualizing ML architectures
• Lobe (video) - "Build, train, and ship custom deep learning models using a simple visual interface."
• Serrano - "A graph computation framework with Accelerate and Metal support."
• Subgraphs - "Subgraphs is a visual IDE for developing computational graphs."
• Machine - "Machine is a machine learning IDE."
• PyTorch - "Tensors and Dynamic neural networks in Python with strong GPU acceleration."
• Sonnet - "Sonnet is a library built on top of TensorFlow for building complex neural networks."
• TensorGraph - "TensorGraph is a framework for building any imaginable models based on TensorFlow"
• nngraph - "graphical computation for nn library in Torch"
• DNNGraph - "a deep neural network model generation DSL in Haskell"
• NNVM - "Intermediate Computational Graph Representation for Deep Learning Systems"
• DeepRosetta - "An universal deep learning models conversor"
• TensorBuilder - "a functional fluent immutable API based on the Builder Pattern"
• Keras - "minimalist, highly modular neural networks library"
• PrettyTensor - "a high level builder API"
• TF-Slim - "a lightweight library for defining, training and evaluating models"
• TFLearn - "modular and transparent deep learning library"
• Caffe - "deep learning framework made with expression, speed, and modularity in mind"