Larissa Driemeier
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Larissa Driemeier has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Josete Barbosa Cruz Meira
School of Dentistry, Department of Biomaterials and Oral Biology, University of São Paulo, São Paulo, Brazil
4 shared publications Marcílio Alves
4 shared publications- Arturo Forner-Cordero
Universidade de São Paulo
3 shared publications - Claudia Comi
Department of Civil and Environmental Engineering, Politecnico di Milano, Milan, Italy
3 shared publications - Eric Cito Becman
Biomechatronics Laboratory, Escola Politécnica, University of Sao Paulo, São Carlos 13566-590, SP, Brazil
3 shared publications Michael Brünig
3 shared publications
Latest Publications
- 22 January 2026
- Published by Elsevier in The Journal of Prosthetic Dentistry
- Vol. 135 (6) , e190-e197
Application of convolutional neural networks for nasofacial reconstruction
- 22 January 2026
- Published by Elsevier in The Journal of Prosthetic Dentistry
- Vol. 135 (6) , e190-e197
Application of convolutional neural networks for nasofacial reconstruction
- Open Access
1 bit is all we need: binary normalized neural networks
The increasing size of large neural network models, specifically language models and foundational image models, poses deployment challenges, prompting efforts to reduce memory requirements and enhance computational efficiency. These efforts are critical to ensure practical deployment and effective utilization of these models across various applications. In this work, a novel type of neural network layers and models is developed that uses only single-bit parameters. In this novel type of models all parameters of all layers, including kernel weights and biases, only have values equal to zero or one. This novel type of models uses layers named as binary normalized layer. These binary normalized layers can be of any type, such as fully connected, convolutional, attention, etc., and they consist of slight variations of the corresponding conventional layers. To show the effectiveness of the binary normalized layers, two different models are configured to solve a multiclass image classification problem and a language decoder to predict the next token of a sequence. The model to solve the image classification has convolutional and fully connected layers, and the language model is composed of transformer blocks with multi-head attention. The results show that models with binary normalized layers present almost the same results obtained by equivalent models with real 32-bit parameters. The binary normalized layers allow to develop models that use 32 times less memory than current models and have equivalent performance. Besides, the binary normalized layers can be easily implemented on current computers using 1-bit arrays, and do not require the development of dedicated electronic hardware. This novel type of layers opens a new era for large neural network models with reduced memory requirements that can be deployed using simple and cheap hardware, such as mobile devices or only cpus.
Open Access1 bit is all we need: binary normalized neural networks
The increasing size of large neural network models, specifically language models and foundational image models, poses deployment challenges, prompting efforts to reduce memory requirements and enhance computational efficiency. These efforts are critical to ensure practical deployment and effective utilization of these models across various applications. In this work, a novel type of neural network layers and models is developed that uses only single-bit parameters. In this novel type of models all parameters of all layers, including kernel weights and biases, only have values equal to zero or one. This novel type of models uses layers named as binary normalized layer. These binary normalized layers can be of any type, such as fully connected, convolutional, attention, etc., and they consist of slight variations of the corresponding conventional layers. To show the effectiveness of the binary normalized layers, two different models are configured to solve a multiclass image classification problem and a language decoder to predict the next token of a sequence. The model to solve the image classification has convolutional and fully connected layers, and the language model is composed of transformer blocks with multi-head attention. The results show that models with binary normalized layers present almost the same results obtained by equivalent models with real 32-bit parameters. The binary normalized layers allow to develop models that use 32 times less memory than current models and have equivalent performance. Besides, the binary normalized layers can be easily implemented on current computers using 1-bit arrays, and do not require the development of dedicated electronic hardware. This novel type of layers opens a new era for large neural network models with reduced memory requirements that can be deployed using simple and cheap hardware, such as mobile devices or only cpus.
- 26 June 2025
- Published by Elsevier in Neural Networks
- Vol. 191, 107763
Neural networks with low-resolution parameters
- 26 June 2025
- Published by Elsevier in Neural Networks
- Vol. 191, 107763
Neural networks with low-resolution parameters
- Open Access
Low-Resolution Neural Networks
The expanding scale of large neural network models introduces significant challenges, driving efforts to reduce memory usage and enhance computational efficiency. Such measures are crucial to ensure the practical implementation and effective application of these sophisticated models across a wide array of use cases. This study examines the impact of parameter bit precision on model performance compared to standard 32-bit models, with a focus on multiclass object classification in images. The models analyzed include those with fully connected layers, convolutional layers, and transformer blocks, with model weight resolution ranging from 1 bit to 4.08 bits. The findings indicate that models with lower parameter bit precision achieve results comparable to 32-bit models, showing promise for use in memory-constrained devices. While low-resolution models with a small number of parameters require more training epochs to achieve accuracy comparable to 32-bit models, those with a large number of parameters achieve similar performance within the same number of epochs. Additionally, data augmentation can destabilize training in low-resolution models, but including zero as a potential value in the weight parameters helps maintain stability and prevents performance degradation. Overall, 2.32-bit weights offer the optimal balance of memory reduction, performance, and efficiency. However, further research should explore other dataset types and more complex and larger models. These findings suggest a potential new era for optimized neural network models with reduced memory requirements and improved computational efficiency, though advancements in dedicated hardware are necessary to fully realize this potential.
Open AccessLow-Resolution Neural Networks
The expanding scale of large neural network models introduces significant challenges, driving efforts to reduce memory usage and enhance computational efficiency. Such measures are crucial to ensure the practical implementation and effective application of these sophisticated models across a wide array of use cases. This study examines the impact of parameter bit precision on model performance compared to standard 32-bit models, with a focus on multiclass object classification in images. The models analyzed include those with fully connected layers, convolutional layers, and transformer blocks, with model weight resolution ranging from 1 bit to 4.08 bits. The findings indicate that models with lower parameter bit precision achieve results comparable to 32-bit models, showing promise for use in memory-constrained devices. While low-resolution models with a small number of parameters require more training epochs to achieve accuracy comparable to 32-bit models, those with a large number of parameters achieve similar performance within the same number of epochs. Additionally, data augmentation can destabilize training in low-resolution models, but including zero as a potential value in the weight parameters helps maintain stability and prevents performance degradation. Overall, 2.32-bit weights offer the optimal balance of memory reduction, performance, and efficiency. However, further research should explore other dataset types and more complex and larger models. These findings suggest a potential new era for optimized neural network models with reduced memory requirements and improved computational efficiency, though advancements in dedicated hardware are necessary to fully realize this potential.
- 26 July 2024
- Published by Elsevier in Structures
- Vol. 67
Wasserstein generative adversarial networks for topology optimization
- 26 July 2024
- Published by Elsevier in Structures
- Vol. 67
Wasserstein generative adversarial networks for topology optimization
- Open Access
- 27 April 2024
- Published by MDPI AG in Biomimetics
- Vol. 9 (5) , 265
Biped Gait Stability Classification Based on the Predicted Step Viability
In this paper, we address the challenge of ensuring stability in bipedal walking robots and exoskeletons. We explore the feasibility of real-time implementation for the Predicted Step Viability algorithm (PSV), a complex multi-step optimization criterion for planning future steps in bipedal gait. To overcome the high computational cost of the PSV algorithm, we performed an analysis using 11 classification algorithms and a stacking strategy to predict if a step will be stable or not. We generated three datasets of increasing complexity through PSV simulations to evaluate the classification performance. Among the classifiers, k Nearest Neighbors, Support Vector Machine with Radial Basis Function Kernel, Decision Tree, and Random Forest exhibited superior performance. Multi-Layer Perceptron also consistently performed well, while linear-based algorithms showed lower performance. Importantly, the use of stacking did not significantly improve performance. Our results suggest that the feature vector applied with this approach is applicable across various robotic models and datasets, provided that training data is balanced and sufficient points are used. Notably, by leveraging classifiers, we achieved rapid computation of results in less than 1 ms, with minimal computational cost.
- 27 April 2024
- Published by MDPI AG in Biomimetics
- Vol. 9 (5) , 265
Open AccessBiped Gait Stability Classification Based on the Predicted Step Viability
In this paper, we address the challenge of ensuring stability in bipedal walking robots and exoskeletons. We explore the feasibility of real-time implementation for the Predicted Step Viability algorithm (PSV), a complex multi-step optimization criterion for planning future steps in bipedal gait. To overcome the high computational cost of the PSV algorithm, we performed an analysis using 11 classification algorithms and a stacking strategy to predict if a step will be stable or not. We generated three datasets of increasing complexity through PSV simulations to evaluate the classification performance. Among the classifiers, k Nearest Neighbors, Support Vector Machine with Radial Basis Function Kernel, Decision Tree, and Random Forest exhibited superior performance. Multi-Layer Perceptron also consistently performed well, while linear-based algorithms showed lower performance. Importantly, the use of stacking did not significantly improve performance. Our results suggest that the feature vector applied with this approach is applicable across various robotic models and datasets, provided that training data is balanced and sufficient points are used. Notably, by leveraging classifiers, we achieved rapid computation of results in less than 1 ms, with minimal computational cost.
- 27 December 2023
- Published by Springer Nature in Soft Computing
- Vol. 28 (9-10) , 6937-6951
On the use of AI for metamodeling: a case study of a 3D bar structure
- 27 December 2023
- Published by Springer Nature in Soft Computing
- Vol. 28 (9-10) , 6937-6951
On the use of AI for metamodeling: a case study of a 3D bar structure
- 20 March 2023
- Published by Elsevier in International Journal of Impact Engineering
- Vol. 176
Slip rate and pressure sensitive friction measurement for crash simulation
- 20 March 2023
- Published by Elsevier in International Journal of Impact Engineering
- Vol. 176
Slip rate and pressure sensitive friction measurement for crash simulation
- 3 February 2023
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 225
Metamodeling of structural failure: Case study of API S-135 steel tube cut in BOP
- 3 February 2023
- Published by Elsevier in Geoenergy Science and Engineering
- Vol. 225
Metamodeling of structural failure: Case study of API S-135 steel tube cut in BOP