Probabilistic HD-CB outperforms binarized HD-CB and approaches full HD-CB performance on synthetic benchmarks using as few as 3 bits per component via random partial updates with time-decaying probability.
Hyperdimensional computing: An introduction to comput- ing in distributed representation with high-dimensional random vectors,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
ImageHD delivers up to 40.4x speedup and 383x energy efficiency for on-device continual learning of visual representations by using hyperdimensional computing and bounded exemplar management on an FPGA.
AMS-HD applies hyperdimensional computing with mutual information feature selection and positional projection to match SVM and MLP accuracy for AMS detection while using far less power, memory, and hardware resources on FPGA and mobile platforms.
citing papers explorer
-
Contextual Bandits for Resource-Constrained Devices using Probabilistic Learning
Probabilistic HD-CB outperforms binarized HD-CB and approaches full HD-CB performance on synthetic benchmarks using as few as 3 bits per component via random partial updates with time-decaying probability.
-
ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing
ImageHD delivers up to 40.4x speedup and 383x energy efficiency for on-device continual learning of visual representations by using hyperdimensional computing and bounded exemplar management on an FPGA.
-
AMS-HD: Hyperdimensional Computing for Real-Time and Energy-Efficient Acute Mountain Sickness Detection
AMS-HD applies hyperdimensional computing with mutual information feature selection and positional projection to match SVM and MLP accuracy for AMS detection while using far less power, memory, and hardware resources on FPGA and mobile platforms.