Self-Governing Neural Networks for On-Device Short Text Classification
This paper is the sequel to the ProjectionNet just above. The SGNN is elaborated on the ProjectionNet, and the optimizations are detailed more in-depth (also see my attempt to reproduce the paper in code and watch the talks' recording).
- from
- Education
- added
- 2026-10-10
- likes
- 0
similar
-
Self Governing Neural Networks (SGNN): the Projection Layer github.com
With this, you can use words in your deep learning models without training nor loading embeddings.
-
ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections arxiv.org
Replace word embeddings by word projections in your deep neural networks, which doesn't require a pre-extracted dictionnary nor storing embedding matrices.
-
The successor representation in human reinforcement learning gershmanlab.com
Nature Human Behavior, 2017. [All Versions].
-
Learning Task-General Representations with Generative Neuro-Symbolic Modeling arxiv.org
ICLR'21, 2021. [All Versions].
-
GAN-CLS github.com
Generative Adversarial Text to Image Synthesis
-
Neural Production Systems arxiv.org
ICML'21, 2021. [All Versions]. Yoshua Bengio's perspective on slot attention model as a general production system.
Education › Papers > Other: “This paper is the sequel to the ProjectionNet just above. The SGNN is elaborated on the ProjectionNet, and the optimizations are detailed more in-depth (also see my attempt to reproduce the paper in code and watch the talks' recording).”