Optimization of the Memory Reset Rate of a Quantum Echo-State Network for Time Sequential Tasks

• URL: http://arxiv.org/abs/2210.01052v1
• Date: Mon, 3 Oct 2022 16:08:06 GMT
• Title: Optimization of the Memory Reset Rate of a Quantum Echo-State Network for Time Sequential Tasks
• Abstract summary: Quantum reservoir computing is a class of quantum machine learning algorithms involving a reservoir of an echo state network based on a register of qubits. We investigate the relation between the memory of the network and the reset rate of the evolution of the quantum reservoir.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum reservoir computing is a class of quantum machine learning algorithms involving a reservoir of an echo state network based on a register of qubits, but the dependence of its memory capacity on the hyperparameters is still rather unclear. In order to maximize its accuracy in time--series predictive tasks, we investigate the relation between the memory of the network and the reset rate of the evolution of the quantum reservoir. We benchmark the network performance by three non--linear maps with fading memory on IBM quantum hardware. The memory capacity of the quantum reservoir is maximized for central values of the memory reset rate in the interval [0,1]. As expected, the memory capacity increases approximately linearly with the number of qubits. After optimization of the memory reset rate, the mean squared errors of the predicted outputs in the tasks may decrease by a factor ~1/5 with respect to previous implementations.

Related papers

• From quantum reservoirs to quantum extreme learning machines through a nearest-neighbor spin chain with tunable quantum memory [0.0]
  We show that the two limits of a single architecture, connected by the input-encoding length, are the number of qubits overwritten with fresh data at each step.<n>We find that recurrent quantum memory is essential when a task must reach far into the past, and dispensable when the relevant history is short.<n>For every task the best reservoirs operate at the edge of chaos, where they perform as well as a densely connected reservoir with random all-to-all couplings of the same size.
  arXiv  Detail & Related papers  (2026-08-28T15:27:38Z)
• Quantum reservoir computing induced by controllable damping [0.9374652839580183]
  We propose an algorithm for inducing damping by applying a controlled rotation to each qubit in a quantum reservoir.<n>It enables tunable, circuit-level amplitude amplification of the zero state.<n>We show that quantum correlations between qubits provide an improvement in terms of memory retention.
  arXiv  Detail & Related papers  (2025-08-20T11:18:57Z)
• Hardware-software co-exploration with racetrack memory based in-memory computing for CNN inference in embedded systems [54.045712360156024]
  racetrack memory is a non-volatile technology that allows high data density fabrication.<n>In-memory arithmetic circuits with memory cells affects both the memory density and power efficiency.<n>We present an efficient in-memory convolutional neural network (CNN) accelerator optimized for use with racetrack memory.
  arXiv  Detail & Related papers  (2025-07-02T07:29:53Z)
• Minimal Quantum Reservoirs with Hamiltonian Encoding [72.27323884094953]
  We investigate a minimal architecture for quantum reservoir computing based on Hamiltonian encoding.<n>This approach circumvents many of the experimental overheads typically associated with quantum machine learning.
  arXiv  Detail & Related papers  (2025-05-28T16:50:05Z)
• Hybrid Quantum Recurrent Neural Network For Remaining Useful Life Prediction [67.410870290301]
  We introduce a Hybrid Quantum Recurrent Neural Network framework, combining Quantum Long Short-Term Memory layers with classical dense layers for Remaining Useful Life forecasting. Experimental results demonstrate that, despite having fewer trainable parameters, the Hybrid Quantum Recurrent Neural Network achieves up to a 5% improvement over a Recurrent Neural Network.
  arXiv  Detail & Related papers  (2025-04-29T14:41:41Z)
• Connection between memory performance and optical absorption in quantum reservoir computing [39.58317527488534]
  dissipation due to material imperfections or coupling to the environment acts as a natural mechanism providing fading memory to reservoir computers. We unravel a connection between the physical metric of optical absorption and the performance of quantum reservoir computers in terms of their short-term memory capacity.
  arXiv  Detail & Related papers  (2025-01-26T16:09:40Z)
• Memory-Efficient 4-bit Preconditioned Stochastic Optimization [53.422307389223626]
  We introduce 4-bit quantization for Shampoo's preconditioners. To our knowledge, this is the first quantization approach applied to Cholesky factors of preconditioners. We demonstrate that combining Cholesky quantization with error feedback enhances memory efficiency and algorithm performance.
  arXiv  Detail & Related papers  (2024-12-14T03:32:54Z)
• Mera: Memory Reduction and Acceleration for Quantum Circuit Simulation via Redundancy Exploration [4.271968023823568]
  We propose a multi-level optimization, namely Mera, to reduce memory usage and accelerate simulation. For a large number of sparse quantum gates, we propose two compressed structures for low-level full-state simulation. Experiments show that our compressed structures increase the number of qubits from 17 to 35, and achieve up to 6.9 times acceleration for QNN.
  arXiv  Detail & Related papers  (2024-11-22T20:07:31Z)
• Solving the time-complexity problem and tuning the performance of quantum reservoir computing by artificial memory restriction [0.0]
  The suitability of quantum reservoir computing for solving temporal tasks is hindered by the collapse of the quantum system when measurements are made. We propose artificially restricting the memory of the quantum reservoir by only using a small number inputs. We numerically study the linear and quadratic algorithms for a fully connected transverse Ising model and a quantum processor model.
  arXiv  Detail & Related papers  (2023-06-22T13:37:34Z)
• Entanglement Distribution in Quantum Repeater with Purification and Optimized Buffer Time [53.56179714852967]
  We explore entanglement distribution using quantum repeaters with optimized buffer time. We observe that increasing the number of memories on end nodes leads to a higher entanglement distribution rate per memory. When imperfect operations are considered, however, we make the surprising observation that the per-memory entanglement rate decreases with increasing number of memories.
  arXiv  Detail & Related papers  (2023-05-23T23:23:34Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Efficient algorithms for quantum information bottleneck [64.67104066707309]
  We propose a new and general algorithm for the quantum generalisation of information bottleneck. Our algorithm excels in the speed and the definiteness of convergence compared with prior results. Notably, we discover that a quantum system can achieve strictly better performance than a classical system of the same size regarding quantum information bottleneck.
  arXiv  Detail & Related papers  (2022-08-22T14:20:05Z)
• Time Series Quantum Reservoir Computing with Weak and Projective Measurements [0.0]
  We show that it is possible to exploit the quantumness of the reservoir and to obtain ideal performance. One consists in rewinding part of the dynamics determined by the fading memory of the reservoir and storing the corresponding data of the input sequence. The other employs weak measurements operating online at the trade-off where information can be extracted accurately and without hindering the needed memory.
  arXiv  Detail & Related papers  (2022-05-13T17:57:39Z)
• Generalized Key-Value Memory to Flexibly Adjust Redundancy in Memory-Augmented Networks [6.03025980398201]
  Memory-augmented neural networks enhance a neural network with an external key-value memory. We propose a generalized key-value memory that decouples its dimension from the number of support vectors. We show that adapting this parameter on demand effectively mitigates up to 44% nonidealities, at equal accuracy and number of devices.
  arXiv  Detail & Related papers  (2022-03-11T19:59:43Z)
• Mesa: A Memory-saving Training Framework for Transformers [58.78933015299703]
  We present Mesa, a memory-saving training framework for Transformers. Mesa uses exact activations during forward pass while storing a low-precision version of activations to reduce memory consumption during training. Experiments on ImageNet, CIFAR-100 and ADE20K demonstrate that Mesa can reduce half of the memory footprints during training.
  arXiv  Detail & Related papers  (2021-11-22T11:23:01Z)
• Memformer: A Memory-Augmented Transformer for Sequence Modeling [55.780849185884996]
  We present Memformer, an efficient neural network for sequence modeling. Our model achieves linear time complexity and constant memory space complexity when processing long sequences.
  arXiv  Detail & Related papers  (2020-10-14T09:03:36Z)
• Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers [76.30674794049293]
  This paper presents an automated mixed-precision quantization flow based on the HAQ framework but tailored for the memory and computational characteristics of MCU devices. Specifically, a Reinforcement Learning agent searches for the best uniform quantization levels, among 2, 4, 8 bits, of individual weight and activation tensors. Given an MCU-class memory bound to 2MB for weight-only quantization, the compressed models produced by the mixed-precision engine result as accurate as the state-of-the-art solutions.
  arXiv  Detail & Related papers  (2020-08-12T06:09:58Z)
• Characterizing the memory capacity of transmon qubit reservoirs [1.5357150519712388]
  Quantum Reservoir Computing exploits the dynamics of quantum ensemble systems for machine learning. In this study, we focus on the task of characterizing the memory capacity of quantum reservoirs built using transmon devices provided by IBM.
  arXiv  Detail & Related papers  (2020-04-15T21:21:36Z)

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.