Academic

We bring LeJEPA to biosignals for the first time and show that the choice of self-supervised objective (masked reconstruction, LeJEPA, or a mix) trades latent-space structure for cross-montage generalisation, all on a 4.6M-parameter bi-Mamba model that is 377× cheaper than LaBraM.

How learned queries and cross-attention let LUNA decouple compute from electrode count, cutting FLOPs by 300× and GPU memory by 10× while still hitting state-of-the-art on TUAR.

An introduction to dilated causal convolutions and a look into how Temporal Convolutional Networks (TCN) function.

Finding the total number of multiply and accumulate operations in a LSTM layer, and looking at how many parameters there are in an LSTM cell.