BiKA: Kolmogorov-Arnold-Network-inspired Ultra Lightweight Neural Network Hardware Accelerator

• URL: http://arxiv.org/abs/2602.23455v1
• Date: Thu, 26 Feb 2026 19:20:55 GMT
• Title: BiKA: Kolmogorov-Arnold-Network-inspired Ultra Lightweight Neural Network Hardware Accelerator
• Abstract summary: We propose BiKA, a multiply-free architecture that replaces nonlinear functions with binary, learnable thresholds.<n>Our FPGA prototype on Ultra96-V2 shows that BiKA reduces hardware resource usage by 27.73% and 51.54% compared with binarized and quantized neural network systolic array accelerators.
• Score: 5.054252675478966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lightweight neural network accelerators are essential for edge devices with limited resources and power constraints. While quantization and binarization can efficiently reduce hardware cost, they still rely on the conventional Artificial Neural Network (ANN) computation pattern. The recently proposed Kolmogorov-Arnold Network (KAN) presents a novel network paradigm built on learnable nonlinear functions. However, it is computationally expensive for hardware deployment. Inspired by KAN, we propose BiKA, a multiply-free architecture that replaces nonlinear functions with binary, learnable thresholds, introducing an extremely lightweight computational pattern that requires only comparators and accumulators. Our FPGA prototype on Ultra96-V2 shows that BiKA reduces hardware resource usage by 27.73% and 51.54% compared with binarized and quantized neural network systolic array accelerators, while maintaining competitive accuracy. BiKA provides a promising direction for hardware-friendly neural network design on edge devices.

Related papers

• Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation [0.0]
  We show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 FPGA can be at least $1.4x$ more energy efficient than the uniform quantisation version.
  arXiv  Detail & Related papers  (2022-09-30T06:33:40Z)
• Hardware Accelerator and Neural Network Co-Optimization for Ultra-Low-Power Audio Processing Devices [0.0]
  HANNAH is a framework for automated and combined hardware/software co-design of deep neural networks and hardware accelerators. We show that HANNAH can find suitable neural networks with minimized power consumption and high accuracy for different audio classification tasks.
  arXiv  Detail & Related papers  (2022-09-08T13:29:09Z)
• A Resource-efficient Spiking Neural Network Accelerator Supporting Emerging Neural Encoding [6.047137174639418]
  Spiking neural networks (SNNs) recently gained momentum due to their low-power multiplication-free computing. SNNs require very long spike trains (up to 1000) to reach an accuracy similar to their artificial neural network (ANN) counterparts for large models. We present a novel hardware architecture that can efficiently support SNN with emerging neural encoding.
  arXiv  Detail & Related papers  (2022-06-06T10:56:25Z)
• FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
  This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task. The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources. It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
  arXiv  Detail & Related papers  (2022-01-18T13:59:22Z)
• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding [67.33850633281803]
  We present a versatile new input encoding that permits the use of a smaller network without sacrificing quality. A small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through a gradient descent. We achieve a combined speed of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds.
  arXiv  Detail & Related papers  (2022-01-16T07:22:47Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch [75.69506249886622]
  Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network.
  arXiv  Detail & Related papers  (2021-02-08T05:55:47Z)
• AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence [111.09105910265154]
  We present a novel minimalist hardware architecture using adder convolutional neural network (AdderNet) The whole AdderNet can practically achieve 16% enhancement in speed. We conclude the AdderNet is able to surpass all the other competitors.
  arXiv  Detail & Related papers  (2021-01-25T11:31:52Z)
• Binary Graph Neural Networks [69.51765073772226]
  Graph Neural Networks (GNNs) have emerged as a powerful and flexible framework for representation learning on irregular data. In this paper, we present and evaluate different strategies for the binarization of graph neural networks. We show that through careful design of the models, and control of the training process, binary graph neural networks can be trained at only a moderate cost in accuracy on challenging benchmarks.
  arXiv  Detail & Related papers  (2020-12-31T18:48:58Z)
• LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput Applications [6.9276012494882835]
  We present a novel method for designing neural network topologies that directly map to a highly efficient FPGA implementation. We show that the combination of sparsity and low-bit activation quantization results in high-speed circuits with small logic depth and low LUT cost.
  arXiv  Detail & Related papers  (2020-04-06T22:15:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.