no code implementations • 8 Feb 2022 • THEIVENDIRAM PRANAVAN, Terence Sim, ArulMurugan Ambikapathi, Savitha Ramasamy
Next, the latent representations for the succeeding instants obtained through non-linear transformations of these context vectors, are contrasted with the latent representations of the encoder for the multi-variables such that the density for the positive pair is maximized.
no code implementations • 25 Sep 2019 • THEIVENDIRAM PRANAVAN, Terence Sim
This work proposes a model-agnostic continual learning framework which can be used with neural networks as well as decision trees to incorporate continual learning.