Dense Morphological Network: An Universal Function Approximator

ICLR 2019 Ranjan MondalSanchayan SantraBhabatosh Chanda

Artificial neural networks are built on the basic operation of linear combination and non-linear activation function. Theoretically this structure can approximate any continuous function with three layer architecture... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Evaluation Results from the Paper


 SOTA for Representation Learning on Circle Data (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Representation Learning Circle Data Morphological Network Accuracy 97.3 # 1