Marco Matta

Dr. Marco Matta


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 December 2019 in IEEE Access
Verified
Journal Article
Open access
Sergio SpanòSergio Spanò
Sergio Spanò
GCGian Carlo Cardarilli
Gian Carlo Cardarilli
Luca Di NunzioLuca Di Nunzio
Luca Di Nunzio
RFRocco Fazzolari
Rocco Fazzolari
DGDaniele Giardino
Daniele Giardino
MRMarco Re
Marco Re
In this paper we propose an efficient hardware architecture that implements the Q-Learning algorithm, suitable for real-time applications. Its main features are low-power, high throughput and limited hardware resources. We also propose a technique based on approximated multipliers to reduce the hardware complexity of the algorithm. We implemented the design on a Xilinx Zynq Ultrascale+ MPSoC ZCU106 Evaluation Kit. The implementation results are evaluated in terms of hardware resources, throughput and power consumption. The architecture is compared to the state of the art of Q-Learning hardware accelerators presented in the literature obtaining better results in speed, power and hardware resources. Experiments using different sizes for the Q-Matrix and different wordlengths for the fixed point arithmetic are presented. With a Q-Matrix of size 8×4 (8 bit data) we achieved a throughput of 222 MSPS (Mega Samples Per Second) and a dynamic power consumption of 37 mW, while with a Q-Matrix of size 256×16 (32 bit data) we achieved a throughput of 93 MSPS and a power consumption 611 mW. Due to the small amount of hardware resources required by the accelerator, our system is suitable for multi-agent IoT applications. Moreover, the architecture can be used to implement the SARSA (State-Action-Reward-State-Action) Reinforcement Learning algorithm with minor modifications.

17 January 2019 in International Journal on Advanced Science, Engineering and Information Technology
Verified
Journal Article
Open access
PDF file
DGDaniele Giardino
Daniele Giardino
MMMarco Matta
Marco Matta
FSFrancesca Silvestri
Francesca Silvestri
Sergio SpanòSergio Spanò
Sergio Spanò
VTValerio Trobiani
Valerio Trobiani
Convolutional Neural Networks (CNNs) are the state-of-the-art in computer vision for different purposes such as image and video classification, recommender systems and natural language processing. The connectivity pattern between CNNs neurons is inspired by the structure of the animal visual cortex. In order to allow the processing, they are realized with multiple parallel 2-dimensional FIR filters that convolve the input signal with the learned feature maps. For this reason, a CNN implementation requires highly parallel computations that cannot be achieved using traditional general-purpose processors, which is why they benefit from a very significant speed-up when mapped and run on Field Programmable Gate Arrays (FPGAs). This is because FPGAs offer the capability to design full customizable hardware architectures, providing high flexibility and the availability of hundreds to thousands of on-chip Digital Signal Processing (DSP) blocks. This paper presents an FPGA implementation of a hand-written number recognition system based on CNN. The system has been characterized in terms of classification accuracy, area, speed, and power consumption. The neural network was implemented on a Xilinx XC7A100T FPGA, and it uses 29.69% of Slice LUTs, 4.42% of slice registers and 52.50% block RAMs. We designed the system using a 9-bit representation that allows for avoiding the use of DSP. For this reason, multipliers are implemented using LUTs. The proposed architecture can be easily scaled on different FPGA devices thank its regularity. CNN can reach a classification accuracy of 90%.

20 July 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Gian Carlo Cardarilli Gian Carlo Cardarilli
Gian Carlo Cardarilli
Luca Di NunzioLuca Di Nunzio
Luca Di Nunzio
RFRocco Fazzolari
Rocco Fazzolari
DGDaniele Giardino
Daniele Giardino
MMMarco Matta
Marco Matta
LSLorenzo Simone
Lorenzo Simone
Microwave tracking, usually performed by on ground processing of the signals coming from a spacecraft, represents a crucial aspect in every deep-space mission. Various noise sources, including receiver noise, affect these signals, limiting the accuracy of the radiometric measurements obtained from the radio link. There are several methods used for spacecraft tracking, including the Delta-Differential One-Way Ranging ( Δ DOR) technique. In the past years, European Space Agency (ESA) missions relied on a narrowband Δ DOR system for navigation in the cruise phase. To limit the adverse effect of nonlinearities in the receiving chain, an innovative wideband approach to Δ DOR measurements has recently been proposed. This work presents the hardware implementation of a new version of the ESA X/Ka Deep Space Transponder based on the new tracking technique named Wideband Δ DOR (W- Δ DOR). The architecture of the new transponder guarantees backward compatibility with narrowband Δ DOR.

1 May 2019 in Electronics Letters
Verified
Journal Article
Open access
PDF file
MMMarco Matta
Marco Matta
GCG.C. Cardarilli
G.C. Cardarilli
Luca Di NunzioLuca Di Nunzio
Luca Di Nunzio
RFRocco Fazzolari
Rocco Fazzolari
DGD. Giardino
D. Giardino
Sergio SpanòSergio Spanò
Sergio Spanò
The authors introduce a novel approach for swarm reinforcement learning that extends the standard Q‐learning to multi‐agent systems. State‐of‐the‐art methods implement a knowledge sharing mechanism between the agents that is triggered by the episodes succession. This causes an intrinsic limit in the convergence speed of the algorithms. They overcame this issue by developing a Q‐learning real‐time swarm algorithm (Q‐RTS), which is iteration‐based and suitable for real‐time systems. Q‐RTS was tested in different environments and compared to other related methods in the literature. They obtained positive results in terms of learning time and scalability, i.e. achieving a speed‐up factor of at least 1.49 with respect to standard Q‐learning. Moreover, Q‐RTS shows enhanced learning performance as the environments complexity increases.

29 August 2019 in IEEE Access
Verified
Journal Article
Open access
MMMarco Matta
Marco Matta
GCGian Carlo Cardarilli
Gian Carlo Cardarilli
Luca Di NunzioLuca Di Nunzio
Luca Di Nunzio
RFRocco Fazzolari
Rocco Fazzolari
DGDaniele Giardino
Daniele Giardino
Sergio SpanòSergio Spanò
Sergio Spanò
Machine Learning (ML) based on supervised and unsupervised learning models has been recently applied in the telecommunication field. However, such techniques rely on application-specific large datasets and the performance deteriorates if the statistics of the inference data changes over time. Reinforcement Learning (RL) is a solution to these issues because it is able to adapt its behavior to the changing statistics of the input data. In this work, we propose the design of an RL Agent able to learn the behavior of a Timing Recovery Loop (TRL) through the Q-Learning algorithm. The Agent is compatible with popular PSK and QAM formats. We validated the RL synchronizer by comparing it to the Mueller and Müller TRL in terms of Modulation Error Ratio (MER) in a noisy channel scenario. The results show a good trade-off in terms of MER performance. The RL based synchronizer loses less than 1 dB of MER with respect to the conventional one but it is able to adapt its behavior to different modulation formats without the need of any tuning for the system parameters.

1 June 2019 in TELKOMNIKA (Telecommunication Computing Electronics and Control)
Verified
Journal Article
Open access
PDF file
GCGian Carlo Cardarilli
Gian Carlo Cardarilli
Luca Di NunzioLuca Di Nunzio
Luca Di Nunzio
RFRocco Fazzolari
Rocco Fazzolari
DGDaniele Giardino
Daniele Giardino
MMMarco Matta
Marco Matta
Sergio SpanòSergio Spanò
Sergio Spanò
This paper investigates about the possibility to reduce power consumption in Neural Network using approximated computing techniques. Authors compare a traditional fixed-point neuron with an approximated neuron composed of approximated multipliers and adder. Experiments show that in the proposed case of study (a wine classifier) the approximated neuron allows to save up to the 43% of the area, a power consumption saving of 35% and an improvement in the maximum clock frequency of 20%.