Tuesday, December 5, 2023, @ 8:00-9:00am PT you are invited to attend an INRC Forum talk from Michael Jurado of GA Tech.

Title:
Spikemoid loss and the sparsification training.

Abstract:
Spiking Neural Networks (SNNs) have gained research attention in recent years due to their potential as low-power computing architectures for deployment on neuromorphic hardware. The introduction of offline training capabilities like Spike Layer Error Reassignment in Time (SLAYER) and advancements in the probabilistic interpretations of SNN output reinforce SNNs as a viable alternative to Artificial Neural Networks (ANNs). Spikemax was previously introduced as a family of differentiable loss methods which use windowed spike counts to form classification probabilities. We modify the spikemax s loss method to use rates and a scaling parameter instead of counts to form scaled-spikemax. Our mathematical analysis shows that an appropriate scaling term can yield less coarse probability outputs from the SNN and help smooth the gradient of the loss during training. Experimentally, we show that scaled-spikemax achieves faster training convergence than spikemax and results in relative improvements of 4.2% and 9.9% in accuracy for NMNIST and N-TIDIGITS18, respectively We then extend scaled-spikemax to construct a spike-based loss function for multi-label classification called spikemoid. The viability of spikemoid is shown via the first known multi-label classification results on N-TIDIGITS18 and 2NMNIST, a novel variation of NMNIST that superimposes event-driven sensory data.

Meeting link to join is available to INRC members and affiliates on the /wiki/spaces/forum/pages/1983578113.

If you are not yet a member of the INRC, please see the “Joining the INRC link” below.

Bio: TBD

Recording:

For the recording and slides, see the full /wiki/spaces/forum/pages/1983578113 (accessible only to INRC Affiliates and Engaged Members).

If you are interested in becoming a member, here is the information about ”Joining the INRC.”