LightFF: Lightweight Inference for Forward-Forward Algorithm
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910583500046336 |
|---|---|
| author | Aminifar, Amin Huang, Baichuan Abtahi, Azra Aminifar, Amir |
| author_facet | Aminifar, Amin Huang, Baichuan Abtahi, Azra Aminifar, Amir |
| contents | The human brain performs tasks with an outstanding energy efficiency, i.e., with approximately 20 Watts. The state-of-the-art Artificial/Deep Neural Networks (ANN/DNN), on the other hand, have recently been shown to consume massive amounts of energy. The training of these ANNs/DNNs is done almost exclusively based on the back-propagation algorithm, which is known to be biologically implausible. This has led to a new generation of forward-only techniques, including the Forward-Forward algorithm. In this paper, we propose a lightweight inference scheme specifically designed for DNNs trained using the Forward-Forward algorithm. We have evaluated our proposed lightweight inference scheme in the case of the MNIST and CIFAR datasets, as well as two real-world applications, namely, epileptic seizure detection and cardiac arrhythmia classification using wearable technologies, where complexity overheads/energy consumption is a major constraint, and demonstrate its relevance. Our code is available at https://github.com/AminAminifar/LightFF. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05241 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LightFF: Lightweight Inference for Forward-Forward Algorithm Aminifar, Amin Huang, Baichuan Abtahi, Azra Aminifar, Amir Machine Learning The human brain performs tasks with an outstanding energy efficiency, i.e., with approximately 20 Watts. The state-of-the-art Artificial/Deep Neural Networks (ANN/DNN), on the other hand, have recently been shown to consume massive amounts of energy. The training of these ANNs/DNNs is done almost exclusively based on the back-propagation algorithm, which is known to be biologically implausible. This has led to a new generation of forward-only techniques, including the Forward-Forward algorithm. In this paper, we propose a lightweight inference scheme specifically designed for DNNs trained using the Forward-Forward algorithm. We have evaluated our proposed lightweight inference scheme in the case of the MNIST and CIFAR datasets, as well as two real-world applications, namely, epileptic seizure detection and cardiac arrhythmia classification using wearable technologies, where complexity overheads/energy consumption is a major constraint, and demonstrate its relevance. Our code is available at https://github.com/AminAminifar/LightFF. |
| title | LightFF: Lightweight Inference for Forward-Forward Algorithm |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.05241 |