Masatoshi Ishii
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Masatoshi Ishii has a total of 92 co-authors. Here are the top co-authors by number of shared publications:
- Atsuya Okazaki
IBM Research – Tokyo, Saiwai, Japan
6 shared publications - Geoffrey William Burr
IBM Research—Almaden, San Jose, USA
4 shared publications - Akiyo Nomura
Department of Applied Physics and Physico-Informatics, Keio University 1 , Yokohama 223-8522, Japan
3 shared publications - Charles Mackin
IBM Research
3 shared publications - Kazuaki Kurihara
Fujitsu Laboratories Ltd
3 shared publications Kohji Hosokawa
IBM Research
3 shared publications
Latest Publications
- Open Access
- 30 October 2025
- Published by Springer Nature in Research Square
Row-by-row convolutional neural networks for Analog-AI
Analog AI implements the multiply-accumulate operations that dominate deep learning at the location of the weight data, offering orders of magnitude performance and energy improvements over conventional digital systems. However, translating these benefits to the Convolutional Neural Networks (CNN) widely used in applications such as image and speech processing is non-trivial. Significant reuse of both weights and activations, together with the need to extensively rearrange activations between layers, require micro-architectural solutions that span across weight mapping strategy, activation positioning, pipelining between stages, and data transport. In this paper, we describe a weight-stationary Analog AI micro-architecture for Convolutional Neural Networks (CNNs), called Row-By-Row- (RBR-) CNNs and its associated circuits and pipelines. We show a hardware demonstration of RBR-CNNs on a 14nm Analog AI inference chip with Phase Change Memory (PCM), achieving software-equivalent accuracy on the ML Perf Benchmark “Key Word Spotting” task using 4 RBR CNN layers. We show RBR CNNs using Analog AI can achieve 7x–15x latency improvements vs. high performance chips reported on ML Perf, while offering extremely high energy-efficiency – at least two orders of magnitude better than published low-power edge chip results, indicating strong applicability in embedded and mobile settings.
- 30 October 2025
- Published by Springer Nature in Research Square
Open AccessRow-by-row convolutional neural networks for Analog-AI
Analog AI implements the multiply-accumulate operations that dominate deep learning at the location of the weight data, offering orders of magnitude performance and energy improvements over conventional digital systems. However, translating these benefits to the Convolutional Neural Networks (CNN) widely used in applications such as image and speech processing is non-trivial. Significant reuse of both weights and activations, together with the need to extensively rearrange activations between layers, require micro-architectural solutions that span across weight mapping strategy, activation positioning, pipelining between stages, and data transport. In this paper, we describe a weight-stationary Analog AI micro-architecture for Convolutional Neural Networks (CNNs), called Row-By-Row- (RBR-) CNNs and its associated circuits and pipelines. We show a hardware demonstration of RBR-CNNs on a 14nm Analog AI inference chip with Phase Change Memory (PCM), achieving software-equivalent accuracy on the ML Perf Benchmark “Key Word Spotting” task using 4 RBR CNN layers. We show RBR CNNs using Analog AI can achieve 7x–15x latency improvements vs. high performance chips reported on ML Perf, while offering extremely high energy-efficiency – at least two orders of magnitude better than published low-power edge chip results, indicating strong applicability in embedded and mobile settings.
- Open Access
- 30 September 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-11
Demonstration of transformer-based ALBERT model on a 14nm analog AI inference chip
A Lite Bidirectional Encoder Representations from Transformers model is demonstrated on an analog inference chip fabricated at 14nm node with phase change memory. The 7.1 million unique analog weights shared across 12 layers are mapped to a single chip, accurately programmed into the conductance of 28.3 million devices, for this first analog hardware demonstration of a meaningfully large Transformer model. The implemented model achieved near iso-accuracy on the General Language Understanding Evaluation benchmark of seven tasks, despite the presence of weight-programming errors, hardware imperfections, readout noise, and error propagation. The average hardware accuracy was only 1.8% below that of the floating-point reference, with several tasks at full iso-accuracy. Careful fine-tuning of model weights using hardware-aware techniques contributes an average hardware accuracy improvement of 4.4%. Accuracy loss due to conductance drift – measured to be roughly 5% over 30 days – was reduced to less than 1% with a recalibration-based “drift compensation” technique.
- 30 September 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-11
Open AccessDemonstration of transformer-based ALBERT model on a 14nm analog AI inference chip
A Lite Bidirectional Encoder Representations from Transformers model is demonstrated on an analog inference chip fabricated at 14nm node with phase change memory. The 7.1 million unique analog weights shared across 12 layers are mapped to a single chip, accurately programmed into the conductance of 28.3 million devices, for this first analog hardware demonstration of a meaningfully large Transformer model. The implemented model achieved near iso-accuracy on the General Language Understanding Evaluation benchmark of seven tasks, despite the presence of weight-programming errors, hardware imperfections, readout noise, and error propagation. The average hardware accuracy was only 1.8% below that of the floating-point reference, with several tasks at full iso-accuracy. Careful fine-tuning of model weights using hardware-aware techniques contributes an average hardware accuracy improvement of 4.4%. Accuracy loss due to conductance drift – measured to be roughly 5% over 30 days – was reduced to less than 1% with a recalibration-based “drift compensation” technique.
- Open Access
- 11 November 2024
- Published by Wiley in Advanced Intelligent Systems
- Vol. 7 (5)
Energy‐Efficient Hardware Implementation of Spiking‐Restricted Boltzmann Machines Using Pseudo‐Synaptic Sampling
Stochastic sampling is performed to reduce hardware energy consumption and prevent overfitting by reducing parameters, because not all data are required for learning. In this study, a new approach, pseudo‐synaptic sampling (PS2) method, which approximates the conventional synaptic sampling machine (S2M) method through a hardware‐friendly implementation while demonstrating superior efficiency, is introduced. By sampling in front of neurons rather than at each synapse, the PS2 method improves hardware energy efficiency and ensures scalability. Furthermore, it improves energy and area efficiency by eliminating the additional circuit required by other techniques, such as the random walk (RW) method previously used which requires an additional circuit to frequently charge/discharge the membrane potential. Herein, the average firing rate equation for the S2M method is modified to suit the experimental conditions of this study. Through this numerical simulations, it is confirmed that the activation function of the PS2 method aligns with that of the S2M method and verified that the PS2 method can implement stochasticity for restricted Boltzmann machine (RBM) neurons. Experimental validation of the PS2 method, compared to the RW method, for Modified National Institute of Standards and Technology database (MNIST) training and inference on field‐programmable‐gate‐array‐implemented spiking RBM chips reveals promising results. In an MNIST 100‐handwritten digit experiment, the PS2 method exhibits on‐chip training accuracy (92%) comparable to that of the RW method (93%). Furthermore, in the energy consumption analysis, it is shown that the PS2 method reduces power consumption by 94.94% compared to the RW method, highlighting its enhanced power efficiency due to a reduced number of circuit elements. In the investigation into the impact of increasing the frequency at which random bits are generated, it is shown that the RW method experiences accuracy degradation even with slight increases, whereas the PS2 method maintains accuracy over significantly longer periods. This enables further power reduction by allowing for a longer period during random bit generation. In this study, a foundation is laid for maximizing the energy efficiency of spiking neural network processors by optimizing internal noise generation mechanisms.
- 11 November 2024
- Published by Wiley in Advanced Intelligent Systems
- Vol. 7 (5)
Open AccessEnergy‐Efficient Hardware Implementation of Spiking‐Restricted Boltzmann Machines Using Pseudo‐Synaptic Sampling
Stochastic sampling is performed to reduce hardware energy consumption and prevent overfitting by reducing parameters, because not all data are required for learning. In this study, a new approach, pseudo‐synaptic sampling (PS2) method, which approximates the conventional synaptic sampling machine (S2M) method through a hardware‐friendly implementation while demonstrating superior efficiency, is introduced. By sampling in front of neurons rather than at each synapse, the PS2 method improves hardware energy efficiency and ensures scalability. Furthermore, it improves energy and area efficiency by eliminating the additional circuit required by other techniques, such as the random walk (RW) method previously used which requires an additional circuit to frequently charge/discharge the membrane potential. Herein, the average firing rate equation for the S2M method is modified to suit the experimental conditions of this study. Through this numerical simulations, it is confirmed that the activation function of the PS2 method aligns with that of the S2M method and verified that the PS2 method can implement stochasticity for restricted Boltzmann machine (RBM) neurons. Experimental validation of the PS2 method, compared to the RW method, for Modified National Institute of Standards and Technology database (MNIST) training and inference on field‐programmable‐gate‐array‐implemented spiking RBM chips reveals promising results. In an MNIST 100‐handwritten digit experiment, the PS2 method exhibits on‐chip training accuracy (92%) comparable to that of the RW method (93%). Furthermore, in the energy consumption analysis, it is shown that the PS2 method reduces power consumption by 94.94% compared to the RW method, highlighting its enhanced power efficiency due to a reduced number of circuit elements. In the investigation into the impact of increasing the frequency at which random bits are generated, it is shown that the RW method experiences accuracy degradation even with slight increases, whereas the PS2 method maintains accuracy over significantly longer periods. This enables further power reduction by allowing for a longer period during random bit generation. In this study, a foundation is laid for maximizing the energy efficiency of spiking neural network processors by optimizing internal noise generation mechanisms.
- Open Access
- 23 October 2024
- Published by Wiley in Advanced Science
- Vol. 11 (46) , e2406433
Solving Max‐Cut Problem Using Spiking Boltzmann Machine Based on Neuromorphic Hardware with Phase Change Memory
Efficiently solving combinatorial optimization problems (COPs) such as Max‐Cut is challenging because the resources required increase exponentially with the problem size. This study proposes a hardware‐friendly method for solving the Max‐Cut problem by implementing a spiking neural network (SNN)‐based Boltzmann machine (BM) in neuromorphic hardware systems. To implement the hardware‐oriented version of the spiking Boltzmann machine (sBM), the stochastic dynamics of leaky integrate‐and‐fire (LIF) neurons with random walk noise are analyzed, and an innovative algorithm based on overlapping time windows is proposed. The simulation results demonstrate the effective convergence and high accuracy of the proposed method for large‐scale Max‐Cut problems. The proposed method is validated through successful hardware implementation on a 6‐transistor/2‐resistor (6T2R) neuromorphic chip with phase change memory (PCM) synapses. In addition, as an expansion of the algorithm, several annealing techniques and bias split methods are proposed to improve convergence, along with circuit design ideas for efficient evaluation of sampling convergence using cell arrays and spiking systems. Overall, the results of the proposed methods demonstrate the potential of energy‐efficient and hardware‐implementable approaches using SNNs to solve COPs. To the best of the author's knowledge, this is the first study to solve the Max‐Cut problem using an SNN neuromorphic hardware chip.
- 23 October 2024
- Published by Wiley in Advanced Science
- Vol. 11 (46) , e2406433
Open AccessSolving Max‐Cut Problem Using Spiking Boltzmann Machine Based on Neuromorphic Hardware with Phase Change Memory
Efficiently solving combinatorial optimization problems (COPs) such as Max‐Cut is challenging because the resources required increase exponentially with the problem size. This study proposes a hardware‐friendly method for solving the Max‐Cut problem by implementing a spiking neural network (SNN)‐based Boltzmann machine (BM) in neuromorphic hardware systems. To implement the hardware‐oriented version of the spiking Boltzmann machine (sBM), the stochastic dynamics of leaky integrate‐and‐fire (LIF) neurons with random walk noise are analyzed, and an innovative algorithm based on overlapping time windows is proposed. The simulation results demonstrate the effective convergence and high accuracy of the proposed method for large‐scale Max‐Cut problems. The proposed method is validated through successful hardware implementation on a 6‐transistor/2‐resistor (6T2R) neuromorphic chip with phase change memory (PCM) synapses. In addition, as an expansion of the algorithm, several annealing techniques and bias split methods are proposed to improve convergence, along with circuit design ideas for efficient evaluation of sampling convergence using cell arrays and spiking systems. Overall, the results of the proposed methods demonstrate the potential of energy‐efficient and hardware‐implementable approaches using SNNs to solve COPs. To the best of the author's knowledge, this is the first study to solve the Max‐Cut problem using an SNN neuromorphic hardware chip.
- Open Access
- 20 November 2023
- Published by Verein zur Forderung des Open Access Publizierens in den Quantenwissenschaften in Quantum
- Vol. 7, 1184
Synergetic quantum error mitigation by randomized compiling and zero-noise extrapolation for the variational quantum eigensolver
We propose a quantum error mitigation strategy for the variational quantum eigensolver (VQE) algorithm. We find, via numerical simulation, that very small amounts of coherent noise in VQE can cause substantially large errors that are difficult to suppress by conventional mitigation methods, and yet our proposed mitigation strategy is able to significantly reduce these errors. The proposed strategy is a combination of previously reported techniques, namely randomized compiling (RC) and zero-noise extrapolation (ZNE). Intuitively, randomized compiling turns coherent errors in the circuit into stochastic Pauli errors, which facilitates extrapolation to the zero-noise limit when evaluating the cost function. Our numerical simulation of VQE for small molecules shows that the proposed strategy can mitigate energy errors induced by various types of coherent noise by up to two orders of magnitude.
- 20 November 2023
- Published by Verein zur Forderung des Open Access Publizierens in den Quantenwissenschaften in Quantum
- Vol. 7, 1184
Open AccessSynergetic quantum error mitigation by randomized compiling and zero-noise extrapolation for the variational quantum eigensolver
We propose a quantum error mitigation strategy for the variational quantum eigensolver (VQE) algorithm. We find, via numerical simulation, that very small amounts of coherent noise in VQE can cause substantially large errors that are difficult to suppress by conventional mitigation methods, and yet our proposed mitigation strategy is able to significantly reduce these errors. The proposed strategy is a combination of previously reported techniques, namely randomized compiling (RC) and zero-noise extrapolation (ZNE). Intuitively, randomized compiling turns coherent errors in the circuit into stochastic Pauli errors, which facilitates extrapolation to the zero-noise limit when evaluating the cost function. Our numerical simulation of VQE for small molecules shows that the proposed strategy can mitigate energy errors induced by various types of coherent noise by up to two orders of magnitude.
- Top Cited PapersOpen Access
- 23 August 2023
- Published by Springer Nature in Nature
- Vol. 620 (7975) , 768-775
An analog-AI chip for energy-efficient speech recognition and transcription
Models of artificial intelligence (AI) that have billions of parameters can achieve high accuracy across a range of tasks1,2, but they exacerbate the poor energy efficiency of conventional general-purpose processors, such as graphics processing units or central processing units. Analog in-memory computing (analog-AI)3–7 can provide better energy efficiency by performing matrix–vector multiplications in parallel on ‘memory tiles’. However, analog-AI has yet to demonstrate software-equivalent (SWeq) accuracy on models that require many such tiles and efficient communication of neural-network activations between the tiles. Here we present an analog-AI chip that combines 35 million phase-change memory devices across 34 tiles, massively parallel inter-tile communication and analog, low-power peripheral circuitry that can achieve up to 12.4 tera-operations per second per watt (TOPS/W) chip-sustained performance. We demonstrate fully end-to-end SWeq accuracy for a small keyword-spotting network and near-SWeq accuracy on the much larger MLPerf8 recurrent neural-network transducer (RNNT), with more than 45 million weights mapped onto more than 140 million phase-change memory devices across five chips.
- 23 August 2023
- Published by Springer Nature in Nature
- Vol. 620 (7975) , 768-775
Top Cited PapersOpen AccessAn analog-AI chip for energy-efficient speech recognition and transcription
Models of artificial intelligence (AI) that have billions of parameters can achieve high accuracy across a range of tasks1,2, but they exacerbate the poor energy efficiency of conventional general-purpose processors, such as graphics processing units or central processing units. Analog in-memory computing (analog-AI)3–7 can provide better energy efficiency by performing matrix–vector multiplications in parallel on ‘memory tiles’. However, analog-AI has yet to demonstrate software-equivalent (SWeq) accuracy on models that require many such tiles and efficient communication of neural-network activations between the tiles. Here we present an analog-AI chip that combines 35 million phase-change memory devices across 34 tiles, massively parallel inter-tile communication and analog, low-power peripheral circuitry that can achieve up to 12.4 tera-operations per second per watt (TOPS/W) chip-sustained performance. We demonstrate fully end-to-end SWeq accuracy for a small keyword-spotting network and near-SWeq accuracy on the much larger MLPerf8 recurrent neural-network transducer (RNNT), with more than 45 million weights mapped onto more than 140 million phase-change memory devices across five chips.
- 21 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 31 (1) , 114-127
A Heterogeneous and Programmable Compute-In-Memory Accelerator Architecture for Analog-AI Using Dense 2-D Mesh
We introduce a highly heterogeneous and programmable compute-in-memory (CIM) accelerator architecture for deep neural network (DNN) inference. This architecture combines spatially distributed CIM memory array “tiles” for weight-stationary, energy-efficient multiply–accumulate (MAC) operations, together with heterogeneous special-function compute cores for auxiliary digital computation. Massively parallel vectors of neuron activation data are exchanged over short distances using a dense and efficient circuit-switched 2-D mesh, offering full end-to-end support for a wide range of DNN workloads, including CNNs, long-short-term-memory (LSTM), and transformers. We discuss the design of the “analog fabric”—the 2-D grid of tiles and compute cores interconnected by the 2-D mesh—and address the efficiency in both mapping of DNNs onto the hardware and in pipelining of various DNN workloads across a range of batch sizes. We show, for the first time, system-level assessments using projected component parameters for a realistic “analog AI” system, based on dense crossbar arrays of low-power nonvolatile analog memory elements, while incorporating a single common analog fabric design that can scale to large networks by introducing data transport between multiple analog AI chips. Our performance estimates for several networks, including large LSTM and bidirectional encoder representations from transformers (BERT), show highly competitive throughput while offering$40\times $ –$140\times $ higher energy efficiency than NVIDIA A100—thus illustrating the strong promise of analog AI and the proposed architecture for DNN inference applications.- 21 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 31 (1) , 114-127
A Heterogeneous and Programmable Compute-In-Memory Accelerator Architecture for Analog-AI Using Dense 2-D Mesh
We introduce a highly heterogeneous and programmable compute-in-memory (CIM) accelerator architecture for deep neural network (DNN) inference. This architecture combines spatially distributed CIM memory array “tiles” for weight-stationary, energy-efficient multiply–accumulate (MAC) operations, together with heterogeneous special-function compute cores for auxiliary digital computation. Massively parallel vectors of neuron activation data are exchanged over short distances using a dense and efficient circuit-switched 2-D mesh, offering full end-to-end support for a wide range of DNN workloads, including CNNs, long-short-term-memory (LSTM), and transformers. We discuss the design of the “analog fabric”—the 2-D grid of tiles and compute cores interconnected by the 2-D mesh—and address the efficiency in both mapping of DNNs onto the hardware and in pipelining of various DNN workloads across a range of batch sizes. We show, for the first time, system-level assessments using projected component parameters for a realistic “analog AI” system, based on dense crossbar arrays of low-power nonvolatile analog memory elements, while incorporating a single common analog fabric design that can scale to large networks by introducing data transport between multiple analog AI chips. Our performance estimates for several networks, including large LSTM and bidirectional encoder representations from transformers (BERT), show highly competitive throughput while offering$40\times $ –$140\times $ higher energy efficiency than NVIDIA A100—thus illustrating the strong promise of analog AI and the proposed architecture for DNN inference applications.- Open Access
- 22 May 2022
- Published by Wiley in Advanced Intelligent Systems
- Vol. 4 (8)
Pattern Training, Inference, and Regeneration Demonstration Using On‐Chip Trainable Neuromorphic Chips for Spiking Restricted Boltzmann Machine
A fully silicon‐integrated restricted Boltzmann machine (RBM) with an event‐driven contrastive divergence (eCD) training algorithm is implemented using novel stochastic leaky integrate‐and‐fire (LIF) neuron circuits and six‐transistor/2‐PCM‐resistor (6T2R) synaptic unit cells on 90 nm CMOS technology. To elaborate, designed a bidirectional, asynchronous, and parallel pulse‐signaling scheme over an analog‐weighted phase‐change memory (PCM) synapse array to enable spike‐timing‐dependent plasticity (STDP) as a local weight update rule based on eCD is designed. Building upon the initial version of this work, significantly more experimental details are added, such as the on‐chip characterization results of LIF and backward‐LIF (BLIF) and stochasticity of our random walk circuitry. The experimental characterization of these on‐chip stochastic neuron circuits shows a reasonable symmetricity between LIF and BLIF as well as the necessary stochasticity for spiking RBM operation. Fully hardware‐based image classification recorded 93% on‐chip training accuracy from 100 handwritten MNIST digit images. In addition, we experimentally demonstrated the generative characteristics of the RBM by reconstructing partial patterns on hardware. As each synapse and neuron execute its computations in an asynchronous and fully parallel fashion, the chip can perform data‐intensive machine learning (ML) tasks in a power‐efficient manner and take advantage of the sparseness of spiking.
- 22 May 2022
- Published by Wiley in Advanced Intelligent Systems
- Vol. 4 (8)
Open AccessPattern Training, Inference, and Regeneration Demonstration Using On‐Chip Trainable Neuromorphic Chips for Spiking Restricted Boltzmann Machine
A fully silicon‐integrated restricted Boltzmann machine (RBM) with an event‐driven contrastive divergence (eCD) training algorithm is implemented using novel stochastic leaky integrate‐and‐fire (LIF) neuron circuits and six‐transistor/2‐PCM‐resistor (6T2R) synaptic unit cells on 90 nm CMOS technology. To elaborate, designed a bidirectional, asynchronous, and parallel pulse‐signaling scheme over an analog‐weighted phase‐change memory (PCM) synapse array to enable spike‐timing‐dependent plasticity (STDP) as a local weight update rule based on eCD is designed. Building upon the initial version of this work, significantly more experimental details are added, such as the on‐chip characterization results of LIF and backward‐LIF (BLIF) and stochasticity of our random walk circuitry. The experimental characterization of these on‐chip stochastic neuron circuits shows a reasonable symmetricity between LIF and BLIF as well as the necessary stochasticity for spiking RBM operation. Fully hardware‐based image classification recorded 93% on‐chip training accuracy from 100 handwritten MNIST digit images. In addition, we experimentally demonstrated the generative characteristics of the RBM by reconstructing partial patterns on hardware. As each synapse and neuron execute its computations in an asynchronous and fully parallel fashion, the chip can perform data‐intensive machine learning (ML) tasks in a power‐efficient manner and take advantage of the sparseness of spiking.
- 17 April 2007
- Published by Springer Nature in Journal of Electroceramics
- Vol. 21 (1-4) , 99-102
Optical properties of epitaxial plzt thin films
- 17 April 2007
- Published by Springer Nature in Journal of Electroceramics
- Vol. 21 (1-4) , 99-102
Optical properties of epitaxial plzt thin films
- 15 March 2007
- Published by AIP Publishing in Journal of Applied Physics
- Vol. 101 (6) , 066104
Relaxorlike dielectric behavior in Ba0.7Sr0.3TiO3 thin films
We present the results of a systematic dielectric study for sputter deposited barium strontium titanate thin film planar capacitors measured over a wide temperature range of for frequencies between and . Our observations of dielectric loss peaks in the temperature and frequency domains cannot be understood in the typical framework of intrinsic phonon losses. We find that the accepted phenomenological Curie–von Schweidler dielectric behavior (universal relaxation law) in our barium strontium titanate films is only applicable over a narrow temperature range. An excellent fit to the Vogel-Fulcher expression suggests relaxorlike behavior in these films. The activation energy of the observed phenomenon suggests that oxygen ion motion play a role in the apparent relaxor behavior, although further experimental work is required to test this hypothesis.- 15 March 2007
- Published by AIP Publishing in Journal of Applied Physics
- Vol. 101 (6) , 066104
Relaxorlike dielectric behavior in Ba0.7Sr0.3TiO3 thin films
We present the results of a systematic dielectric study for sputter deposited barium strontium titanate thin film planar capacitors measured over a wide temperature range of for frequencies between and . Our observations of dielectric loss peaks in the temperature and frequency domains cannot be understood in the typical framework of intrinsic phonon losses. We find that the accepted phenomenological Curie–von Schweidler dielectric behavior (universal relaxation law) in our barium strontium titanate films is only applicable over a narrow temperature range. An excellent fit to the Vogel-Fulcher expression suggests relaxorlike behavior in these films. The activation energy of the observed phenomenon suggests that oxygen ion motion play a role in the apparent relaxor behavior, although further experimental work is required to test this hypothesis.