118 citations · 151 across the 10 of their papers we have counts for
3 papers · 1 filter
Learning Compositional Structures for Deep Learning: Why Routing-by-agreement is Necessary
Sai Raam Venkatraman, Ankit Anand, S. Balasubramanian +1
A formal description of the compositionality of neural networks is associated directly with the formal grammar-structure of the objects it seeks to represent. This formal grammar-s…
Building Deep, Equivariant Capsule Networks
Sairaam Venkatraman, S. Balasubramanian, R. Raghunatha Sarma
Capsule networks are constrained by the parameter-expensive nature of their layers, and the general lack of provable equivariance guarantees. We present a variation of capsule netw…
RES-SE-NET: Boosting Performance of Resnets by Enhancing Bridge-connections
Varshaneya V, Balasubramanian S, Darshan Gera
One of the ways to train deep neural networks effectively is to use residual connections. Residual connections can be classified as being either identity connections or bridge-conn…