Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Patricio Bulić has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Noise Reduction with Recursive Filtering for More Accurate Parameter Identification of Electrochemical Sources and Interfaces

    by Mitar Simić, Milan Medić, Milan Radovanović, Vladimir Risojević, Patricio Bulić

    Noise reduction is essential in analyzing electrochemical impedance spectroscopy (EIS) data for accurate parameter identification of models of electrochemical sources and interfaces. EIS is widely used to study the behavior of electrochemical systems as it provides information about the processes occurring at electrode surfaces. However, measurement noise can severely compromise the accuracy of parameter identification and the interpretation of EIS data. This paper presents methods for parameter identification of Randles (also known as R-RC or 2R-1C) equivalent electrical circuits and noise reduction in EIS data using recursive filtering. EIS data obtained at the estimated characteristic frequency is processed with three equations in the closed form for the parameter estimation of series resistance, charge transfer resistance, and double-layer capacitance. The proposed recursive filter enhances estimation accuracy in the presence of random noise. Filtering is embedded in the estimation procedure, while the optimal value of the recursive filter weighting factor is self-tuned based on the proposed search method. The distinguished feature is that the proposed method can process EIS data and perform estimation with filtering without any input from the user. Synthetic datasets and experimentally obtained impedance data of lithium-ion batteries were successfully processed using PC-based and microcontroller-based systems.


  • Virtual Memory

    by Patricio Bulić

  • Open Access

    An Energy-efficient and Accuracy-adjustable bfloat16 Multiplier

    by Ratko Pilipović, Patricio Bulić, Uroš Lotrič

    The approximate multipliers have been extensively used in neural network inference, but due to the relatively large error, they have yet to be successfully deployed in neural network learning. Recently, the bfloat16 format has emerged as a viable number representation for neural networks. This paper proposes a novel approximate bfloat16 multiplier with on-the-fly adjustable accuracy for energy-efficient learning in deep neural networks. The size of the proposed multiplier is only 62% of the size of the exact bfloat16 multiplier. Furthermore, its energy footprint is up to five times smaller than the footprint of the exact bfloat16 multiplier. We demonstrate the advantages of the proposed multiplier in deep neural network learning, where we successfully train the ResNet-20 network on the CIFAR-10 dataset from scratch.


  • Open Access

    Energy-efficient neural network learning with accuracy-adjustable floating-point multiplier

    by Ratko Pilipović, Patricio Bulic, Uros Lotrič

    This paper proposes a novel approximate bfloat16 multiplier with on-the-fly adjustable accuracy for energy-efficient learning in deep neural networks. The size of the proposed multiplier is only 62% of the size of the exact bfloat16 multiplier. Furthermore, its energy footprint is up to five times smaller than the footprint of the exact bfloat multiplier. We demonstrate the advantages of the proposed multiplier in deep neural network learning, where we successfully train the ResNet-20 network on the CIFAR-10 dataset from scratch.

  • Open Access

    An Approximate GEMM Unit for Energy-Efficient Object Detection

    by Ratko Pilipović, Vladimir Risojević, Janko Božič, Patricio Bulić, Uroš Lotrič

    Edge computing brings artificial intelligence algorithms and graphics processing units closer to data sources, making autonomy and energy-efficient processing vital for their design. Approximate computing has emerged as a popular strategy for energy-efficient circuit design, where the challenge is to achieve the best tradeoff between design efficiency and accuracy. The essential operation in artificial intelligence algorithms is the general matrix multiplication (GEMM) operation comprised of matrix multiplication and accumulation. This paper presents an approximate general matrix multiplication (AGEMM) unit that employs approximate multipliers to perform matrix–matrix operations on four-by-four matrices given in sixteen-bit signed fixed-point format. The synthesis of the proposed AGEMM unit to the 45 nm Nangate Open Cell Library revealed that it consumed only up to 36% of the area and 25% of the energy required by the exact general matrix multiplication unit. The AGEMM unit is ideally suited to convolutional neural networks, which can adapt to the error induced in the computation. We evaluated the AGEMM units’ usability for honeybee detection with the YOLOv4-tiny convolutional neural network. The results implied that we can deploy the AGEMM units in convolutional neural networks without noticeable performance degradation. Moreover, the AGEMM unit’s employment can lead to more area- and energy-efficient convolutional neural network processing, which in turn could prolong sensors’ and edge nodes’ autonomy.


  • Open Access

    A Hybrid Radix-4 and Approximate Logarithmic Multiplier for Energy Efficient Image Processing

    by Uroš Lotrič, Ratko Pilipović, Patricio Bulić

    Multiplication is an essential image processing operation commonly implemented in hardware DSP cores. To improve DSP cores’ area, speed, or energy efficiency, we can approximate multiplication. We present an approximate multiplier that generates two partial products using hybrid radix-4 and logarithmic encoding of the input operands. It uses the exact radix-4 encoding to generate the partial product from the three most significant bits and the logarithmic approximation with mantissa trimming to approximate the partial product from the remaining least-significant bits. The proposed multiplier fills the gap between highly accurate approximate non-logarithmic multipliers with a complex design and less accurate approximate logarithmic multipliers with a more straightforward design. We evaluated the multiplier’s efficiency in terms of error, energy (power-delay-product) and area utilisation using NanGate 45 nm. The experimental results show that the proposed multiplier exhibits good area utilisation and energy consumption and behaves well in image processing applications.


  • Open Access

    A Two-Stage Operand Trimming Approximate Logarithmic Multiplier

    by Ratko Pilipović, Patricio Bulić, Uroš Lotrič

    We present an approximate logarithmic multiplier with two-stage operand trimming, which prioritises area and energy consumption while retains acceptable accuracy. The multiplier trims the least significant parts of input operands in the first stage and the mantissas of the obtained operands' approximations in the second stage. We evaluated the multiplier's efficiency in terms of error, energy, and area utilisation using NanGate 45nm. The experimental results show that the proposed multiplier exhibits smaller area utilisation and energy consumption than the state-of-the-art designs and that it behaves well in image processing and image classification with convolutional neural networks.


  • Open Access

    On the Design of an Energy Efficient Digital IIR A-Weighting Filter Using Approximate Multiplication

    by Ratko Pilipović, Vladimir Risojević, Patricio Bulić

    This paper presents a new A-weighting filter’s design and explores the potential of using approximate multiplication for low-power digital A-weighting filter implementation. It presents a thorough analysis of the effects of approximate multiplication, coefficient quantization, the order of first-order sections in the filter’s cascade, and zero-pole pairings on the frequency response of the digital A-weighting filter. The proposed A-weighting filter was implemented as a sixth-order IIR filter using approximate odd radix-4 multipliers. The proposed filter was synthesized (Verilog to GDS) using the Nangate45 cell library, and MATLAB simulations were performed to verify the designed filter’s magnitude response and performance. Synthesis results indicate that the proposed design achieves nearly 70% reduction in energy (power-delay product) with a negligible deviation of the frequency response from the floating-point implementation. Experiments on acoustic noise suggest that the proposed digital A-weighting filter can be deployed in environmental noise measurement applications without any notable performance degradation.


  • Open Access

    On the Design of Logarithmic Multiplier Using Radix-4 Booth Encoding

    by Ratko Pilipovic, Patricio Bulic

    This paper proposes an energy-efficient approximate multiplier which combines radix-4 Booth encoding and logarithmic product approximation. Additionally, a datapath pruning technique is proposed and studied to reduce the hardware complexity of the multiplier. Various experiments were conducted to evaluate the multiplier’s error performance and efficiency in terms of energy and area utilization. The reported results are based on simulations using TSMC-180nm. Also, the applicability of the proposed multiplier is examined in image sharpening and convolutional neural networks. The applicability assessment shows that the proposed multiplier can replace an exact multiplier and deliver up to a 75% reduction in energy consumption and up to a 50% reduction in area utilization. Comparative analysis with the state-of-the-art multipliers indicates the potential of the proposed approach as a novel design strategy for approximate multipliers. When compared to the state-of-the-art approximate nonlogarithmic multipliers, the proposed multiplier offers smaller energy consumption with the same level of applicability in image processing and classification applications. On the other hand, some state-of-theart approximate logarithmic multipliers exhibit lower energy consumption than the proposed multiplier but deliver significant performance degradation for the selected application cases.