Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Mtandao wa Vidonge× | Ufumbuzi wa Maarifa× | Utafutaji wa Usanifu wa Neural× | |
|---|---|---|---|
| Nyanja | Ujifunzaji wa Kina | Ujifunzaji wa Kina | Ujifunzaji wa Kina |
| Familia | Machine learning | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2017 | 2015 | 2017 |
| Mwanzilishi≠ | Sabour, S., Frosst, N. & Hinton, G. E. | Hinton, G., Vinyals, O. & Dean, J. | Zoph, B. & Le, Q.V. |
| Aina≠ | Deep learning architecture (vector capsules with dynamic routing) | Neural network compression (teacher–student) | Automated architecture optimization (deep learning) |
| Chanzo asilia≠ | Sabour, S., Frosst, N. & Hinton, G. E. (2017). Dynamic Routing Between Capsules. Advances in Neural Information Processing Systems (NeurIPS). link ↗ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ | Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗ |
| Majina mbadala | Kapsül Ağı (CapsNet), CapsNet, capsule net, dynamic routing network | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search |
| Zinazohusiana≠ | 4 | 5 | 5 |
| Muhtasari≠ | A Capsule Network (CapsNet) is a deep learning architecture introduced by Sara Sabour, Nicholas Frosst and Geoffrey Hinton in 2017 that organises neurons as vectors (capsules) rather than scalar activations, so that spatial hierarchy and pose (orientation) information are encoded directly. It was proposed to overcome the fragility of convolutional networks to changes in viewpoint. | Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster. | Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All. |
| ScholarGateSeti ya data ↗ |
|
|
|