1. |
- Loni, Mohammad, et al.
(författare)
-
Designing compact convolutional neural network for embedded stereo vision systems
- 2018
-
Ingår i: Proceedings - 2018 IEEE 12th International Symposium on Embedded Multicore/Many-Core Systems-on-Chip, MCSoC 2018. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781538666890 ; , s. 244-251
-
Konferensbidrag (refereegranskat)abstract
- Autonomous systems are used in a wide range of domains from indoor utensils to autonomous robot surgeries and self-driving cars. Stereo vision cameras probably are the most flexible sensing way in these systems since they can extract depth, luminance, color, and shape information. However, stereo vision based applications suffer from huge image sizes and computational complexity leading system to higher power consumption. To tackle these challenges, in the first step, GIMME2 stereo vision system [1] is employed. GIMME2 is a high-throughput and cost efficient FPGA-based stereo vision embedded system. In the next step, we present a framework for designing an optimized Deep Convolutional Neural Network (DCNN) for time constraint applications and/or limited resource budget platforms. Our framework tries to automatically generate a highly robust DCNN architecture for image data receiving from stereo vision cameras. Our proposed framework takes advantage of a multi-objective evolutionary optimization approach to design a near-optimal network architecture for both the accuracy and network size objectives. Unlike recent works aiming to generate a highly accurate network, we also considered the network size parameters to build a highly compact architecture. After designing a robust network, our proposed framework maps generated network on a multi/many core heterogeneous System-on-Chip (SoC). In addition, we have integrated our framework to the GIMME2 processing pipeline such that it can also estimate the distance of detected objects. The generated network by our framework offers up to 24x compression rate while losing only 5% accuracy compare to the best result on the CIFAR-10 dataset.
|
|
2. |
- Calderón-Contreras, Rafael, et al.
(författare)
-
A regional PECS node built from place-based social-ecological sustainability research in Latin America and the Caribbean
- 2022
-
Ingår i: Ecosystems and People. - : Informa UK Limited. - 2639-5908 .- 2639-5916. ; 18:1, s. 1-14
-
Tidskriftsartikel (refereegranskat)abstract
- Sustainability requires a combination of meaningful co-production of locally relevant solutions, synthesis of insights gained across regions, and increased cooperation between science, policy and practice. The Programme for Ecosystem Change and Society (PECS) has been coordinating Place-Based Social-Ecological Sustainability Research (PBSESR) across the globe and emphasizes the need for regional scientific nodes from diverse biocultural regions to inform sustainability science and action. In this paper, we assess the strengths of the PBSESR communities in Latin America and the Caribbean (LAC). We provide an overview of PBSESR literature associated with this region and highlight the achievements of two prominent regional networks: The Social-Ecological Systems and Sustainability Research Network from Mexico (SocioEcoS) and the South American Institute for Resilience and Sustainability Studies from Uruguay (SARAS Institute). Finally, we identify the potential in these nodes to constitute a regional PECS node in Latin America and discuss the capacity needed to ensure such function. The results of the literature review show that while still loosely interconnected across the region, networks play key roles in connecting otherwise cloistered teams and we illustrate how the SocioEcoS network (focusing on transdisciplinary co-production of knowledge towards sustainability) and the SARAS Institute (focusing on innovative approaches for looking at complex social-ecological problems, rooted in slow science and arts) operate as key connectors in the region. We conclude that these organizations combined can embody a Latin American node for PECS, and would thereby not only contribute to regional but also global capacities to advance the sustainability agenda.
|
|
3. |
|
|
4. |
- Loni, Mohammad, et al.
(författare)
-
DeepMaker : A multi-objective optimization framework for deep neural networks in embedded systems
- 2020
-
Ingår i: Microprocessors and microsystems. - : Elsevier B.V.. - 0141-9331 .- 1872-9436. ; 73
-
Tidskriftsartikel (refereegranskat)abstract
- Deep Neural Networks (DNNs) are compute-intensive learning models with growing applicability in a wide range of domains. Due to their computational complexity, DNNs benefit from implementations that utilize custom hardware accelerators to meet performance and response time as well as classification accuracy constraints. In this paper, we propose DeepMaker framework that aims to automatically design a set of highly robust DNN architectures for embedded devices as the closest processing unit to the sensors. DeepMaker explores and prunes the design space to find improved neural architectures. Our proposed framework takes advantage of a multi-objective evolutionary approach that exploits a pruned design space inspired by a dense architecture. DeepMaker considers the accuracy along with the network size factor as two objectives to build a highly optimized network fitting with limited computational resource budgets while delivers an acceptable accuracy level. In comparison with the best result on the CIFAR-10 dataset, a generated network by DeepMaker presents up to a 26.4x compression rate while loses only 4% accuracy. Besides, DeepMaker maps the generated CNN on the programmable commodity devices, including ARM Processor, High-Performance CPU, GPU, and FPGA.
|
|
5. |
- Loni, Mohammad, PhD Candidate, 1991-, et al.
(författare)
-
Learning Activation Functions for Sparse Neural Networks
- 2023
-
Ingår i: Proc. Mach. Learn. Res.. - : ML Research Press.
-
Konferensbidrag (refereegranskat)abstract
- Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts while saving significant energy and memory at inference. However, the accuracy drop incurred by SNNs, especially at high pruning ratios, can be an issue in critical deployment conditions. While recent works mitigate this issue through sophisticated pruning techniques, we shift our focus to an overlooked factor: hyperparameters and activation functions. Our analyses have shown that the accuracy drop can additionally be attributed to (i) Using ReLU as the default choice for activation functions unanimously, and (ii) Fine-tuning SNNs with the same hyperparameters as dense counterparts. Thus, we focus on learning a novel way to tune activation functions for sparse networks and combining these with a separate hyperparameter optimization (HPO) regime for sparse networks. By conducting experiments on popular DNN models (LeNet-5, VGG-16, ResNet-18, and EfficientNet-B0) trained on MNIST, CIFAR-10, and ImageNet-16 datasets, we show that the novel combination of these two approaches, dubbed Sparse Activation Function Search, short: SAFS, results in up to 15.53%, 8.88%, and 6.33% absolute improvement in the accuracy for LeNet-5, VGG-16, and ResNet-18 over the default training protocols, especially at high pruning ratios.
|
|
6. |
- Majd, A., et al.
(författare)
-
Improving motion safety and efficiency of intelligent autonomous swarm of drones
- 2020
-
Ingår i: Drones. - : MDPI AG. - 2504-446X. ; 4:3, s. 1-19
-
Tidskriftsartikel (refereegranskat)abstract
- Interest is growing in the use of autonomous swarms of drones in various mission-physical applications such as surveillance, intelligent monitoring, and rescue operations. Swarm systems should fulfill safety and efficiency constraints in order to guarantee dependable operations. To maximize motion safety, we should design the swarm system in such a way that drones do not collide with each other and/or other objects in the operating environment. On other hand, to ensure that the drones have sufficient resources to complete the required task reliably, we should also achieve efficiency while implementing the mission, by minimizing the travelling distance of the drones. In this paper, we propose a novel integrated approach that maximizes motion safety and efficiency while planning and controlling the operation of the swarm of drones. To achieve this goal, we propose a novel parallel evolutionary-based swarm mission planning algorithm. The evolutionary computing allows us to plan and optimize the routes of the drones at the run-time to maximize safety while minimizing travelling distance as the efficiency objective. In order to fulfill the defined constraints efficiently, our solution promotes a holistic approach that considers the whole design process from the definition of formal requirements through the software development. The results of benchmarking demonstrate that our approach improves the route efficiency by up to 10% route efficiency without any crashes in controlling swarms compared to state-of-the-art solutions.
|
|
7. |
- Salimi, M., et al.
(författare)
-
Multi-objective optimization of real-time task scheduling problem for distributed environments
- 2020
-
Ingår i: PROCEEDINGS OF THE 6TH CONFERENCE ON THE ENGINEERING OF COMPUTER BASED SYSTEMS (ECBS 2019). - New York, NY, USA : Association for Computing Machinery. - 9781450376365
-
Konferensbidrag (refereegranskat)abstract
- Real-world applications are composed of multiple tasks which usually have intricate data dependencies. To exploit distributed processing platforms, task allocation and scheduling, that is assigning tasks to processing units and ordering inter-processing unit data transfers, plays a vital role. However, optimally scheduling tasks on processing units and finding an optimized network topology is an NP-complete problem. The problem becomes more complicated when the tasks have real-time deadlines for termination. Exploring the whole search space in order to find the optimal solution is not feasible in a reasonable amount of time, therefore meta-heuristics are often used to find a near-optimal solution. We propose here a multi-population evolutionary approach for near-optimal scheduling optimization, that guarantees end-to-end deadlines of tasks in distributed processing environments. We analyze two different exploration scenarios including single and multi-objective exploration. The main goal of the single objective exploration algorithm is to achieve the minimal number of processing units for all the tasks, whereas a multi-objective optimization tries to optimize two conflicting objectives simultaneously considering the total number of processing units and end-to-end finishing time for all the jobs. The potential of the proposed approach is demonstrated by experiments based on a use case for mapping a number of jobs covering industrial automation systems, where each of the jobs consists of a number of tasks in a distributed environment.
|
|