Shilpak Banerjee

According to our database, Shilpak Banerjee authored at least 9 papers between 2020 and 2022.

Collaborative distances:

• Dijkstra number of six.
• Erdős number of five.

2022

SAU: Smooth Activation Function Using Convolution with Approximate Identities.

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

Proceedings of the Computer Vision - ECCV 2022, 2022

Smooth Maximum Unit: Smooth Activation Function for Deep Networks using Smoothing Maximum Technique.

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions.

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

SMU: smooth activation function for deep networks using smoothing maximum technique.

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

CoRR, 2021

Orthogonal-Padé Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks.

Koushik Biswas, Shilpak Banerjee, Ashish Kumar Pandey

CoRR, 2021

TanhSoft - Dynamic Trainable Activation Functions for Faster Learning and Better Performance.

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

IEEE Access, 2021

EIS - Efficient and Trainable Activation Functions for Better Accuracy and Performance.

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2021, 2021

2020

EIS - a family of activation functions combining Exponential, ISRU, and Softplus.

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

CoRR, 2020

TanhSoft - a family of activation functions combining Tanh and Softplus.

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

CoRR, 2020