Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Condition-Aware Neural Networks for Image Generation: a paper dive
Published:
An explanation of the paper “Condition-Aware Neural Networks for Image Generation”.
Insights from a Computer Science conference: DATE 2024
Published:
Diary-like post about my experience at the DATE 2024 conference.
Auto-Tuning for Deep Neural Network Deployment
Published:
Explanation of the auto-tuning concept for deployment of Neural Networks.
Green AI: Methods and Solutions to Improve AI Sustainability
Published:
Communication and opinion article about techniques to enable Green AI.
Galactica: how to (responsibly) use the controversial language model everyone is talking about
Published:
Communication and opinion article, talking about the contents of paper Galactica: A Large Language Model for Science.
How DeepMind discovered new ways of multiplying matrices using AI
Published:
Communication article, explaining the contents of paper Discovering faster matrix multiplication algorithms with reinforcement learning.
Hardware Accelerators for Neural Networks: How systolic arrays work
Published:
Educational article, explaining how systolic arrays are used to execute the basic matrix multiplication operation, and how they can be used to build entire hardware accelerators to execute neural network operators.
Batch normalization: theory and how to use it with Tensorflow
Published:
Small technical post about how to use the batch normalization layer in Tensorflow.
portfolio
Portfolio item number 1
Published:
Short description of portfolio item number 1
Portfolio item number 2
Published:
Short description of portfolio item number 2
publications
HAPM - Hardware Aware Pruning Method for CNN hardware accelerators in resource constrained devices
Published in arXiv, 2021
Paper result from the thesis for the title of Electronic Engineer attained in 2021 at the Universidad Tecnologica Nacional (UTN), Argentina.
Download here
Integration of a systolic array based hardware accelerator into a DNN operator auto-tuning framework
Published in ESWEEK Workshop: CODAI 2023, 2022
This paper explains the integration added to the TVM framework to generate C code to accelerate neural networks on the Gemmini accelerator
Download here
Low-Power Traffic Surveillance using Multiple RGB and Event Cameras: A Survey
Published in IEEE International Smart Cities Conference (ISC2) 2023, 2023
This paper presents a survey on methods and techniques for traffic surveillance using multiple POV cameras.
Download here
Characterization of Execution Time Variability in FPGA-Based AI-Accelerators
Published in 2023 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), 2023
This paper presents a comparison of execution time of different Neural Networks on different FPGA-based open source AI Accelerators.
Download here
DIAPASON: Differentiable Allocation, Partitioning and Fusion of Neural Networks for Distributed Inference
Published in Design, Automation and Test in Europe Conference, 2024
This paper presents a new method to model the problem of distributing the inference of a NN across multiple devices.
Download here
Iterative Filter Pruning for Concatenation-based CNN Architectures
Published in , 2024
A method to prune in an iterative manner CNNs, taking into account the connectivity graph of layers.
Download here
Embedded Distributed Inference of Deep Neural Networks: A Systematic Review
Published in arXiv, 2024
This paper presents a systematic review of papers distributing the execution of CNNs across multiple devices.
Download here
Efficient Edge AI: Deploying Convolutional Neural Networks on FPGA with the Gemmini Accelerator
Published in 27th Euromicro Conference Series on Digital System Design (DSD) 2024, 2024
This paper presents a workflow for deployment of CNNs on custom hardware accelerators, taken into account pruning, quantization, and tuning. The workflow was realized using TVM.
Download here
talks
teaching
Teaching assistant at UTN, course “Digital Techniques 3”
Graduate course, National Technological University (UTN), Department of Electronics, 2021
I was a teaching assistant on course “Digital Techniques 3”, working for Prof. Ing. Alejandro Furfaro. I was in charge of the applied side of the course, where we worked on baremetal programming and embedded Linux for ARM.