DendroNN: Dendrocentric Neural Networks for Energy-Efficient Classification of Event-Based Data

TL;DR

A novel approach to low-power spatiotemporal processing on event-driven hardware by leveraging a DendroNN's dynamic and static sparsity along with intrinsic quantization, which achieves up to 4x higher efficiency than state-of-the-art neuromorphic hardware at comparable accuracy on the same audio classification task, demonstrating its suitability for spatiotemporal event-based computing.

Abstract

Spatiotemporal information is at the core of diverse sensory processing and computational tasks. Feed-forward spiking neural networks can be used to solve these tasks while offering potential benefits in terms of energy efficiency by computing event-based. However, they have trouble decoding temporal information with high accuracy. Thus, they commonly resort to recurrence or delays to enhance their temporal computing ability which, however, bring downsides in terms of hardware-efficiency. In the brain, dendrites are computational powerhouses that just recently started to be acknowledged in such machine learning systems. In this work, we focus on a sequence detection mechanism present in branches of dendrites and translate it into a novel type of neural network by introducing a dendrocentric neural network, DendroNN. DendroNNs identify unique incoming spike sequences as spatiotemporal features. This work further introduces a rewiring phase to train the non-differentiable spike sequences without the use of gradients. During the rewiring, the network memorizes frequently occurring sequences and additionally discards those that do not contribute any discriminative information. The networks display competitive accuracies across various event-based time series datasets. We also propose an asynchronous digital hardware architecture using a time-wheel mechanism that builds on the event-driven design of DendroNNs, eliminating per-step global updates typical of delay- or recurrence-based models. By leveraging a DendroNN's dynamic and static sparsity along with intrinsic quantization, it achieves up to 4x higher efficiency than state-of-the-art neuromorphic hardware at comparable accuracy on the same audio classification task, demonstrating its suitability for spatiotemporal event-based computing. This work offers a novel approach to low-power spatiotemporal processing on event-driven hardware.

Figures (7)

• Figure 1: (a) Schematic of the network architecture. Sparse, binary connections route input spikes $x$ to a set of hidden units, each tuned to a specific spatiotemporal pattern. (b) Example of sequence detection for $N_s = 3$. A hidden unit responds only when spikes arrive from the correct spatial origins $\tilde{x_0},\tilde{x_1},\tilde{x_2}$ in the prescribed temporal order, with inter-spike intervals $\Delta t_1$ and $\Delta t_2$. Inputs that are out of order or mistimed are suppressed. When the full target sequence is observed, the unit emits a single output spike.
• Figure 2: Exemplary input spike patterns and model responses. (a) All input spikes arrive from the correct spatial channels and in the prescribed temporal order, with the required inter-spike intervals $\Delta t_1$ and $\Delta t_2$, resulting in the emission of an output spike. (b) Although the spike order is preserved, deviations in the inter-spike intervals (early or late arrivals) violate the temporal constraints and suppress the output response. (c) Only the spikes belonging to the correctly ordered sequence (red) satisfy the spatiotemporal constraints; spikes from incorrectly ordered sequences do not elicit an output. (d) Multiple sequences can be processed in parallel: irrelevant spikes are inhibited, while all valid target sequences are reliably detected and trigger output events.
• Figure 3: Visualization of the impact of different model parameterizations on its classification performance.
• Figure 4: Visualization of the rewiring phase using the NeuroMorse train set sample "which" as an example. Throughout multiple epochs, initially randomly arranged sequences are rewired and frozen to match existing spatiotemporal patterns in the sample.
• Figure 5: Impact of applying the rewiring phase regarding the model's footprint. In the case of the NeuroMorse dataset, network size can be reduced by 10-100x without suffering accuracy loss. This effect is drastically amplified for datasets of higher spatial and temporal complexity.