A Multi-Teacher Knowledge Distillation Framework with Aggregation Techniques for Lightweight Deep Models

Knowledge Distillation (KD) is a machine learning technique in which a compact student model learns to replicate the performance of a larger teacher model by mimicking its output predictions. Multi-Teacher Knowledge Distillation extends this paradigm by aggregating knowledge from multiple teacher mo...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Ahmed Hamdi, Hassan N. Noura, Joseph Azar
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	MDPI AG 2025-09-01
Σειρά:	Applied System Innovation
Θέματα:	knowledge distillation cross-modal neural network compression downsampling multi-teachers multi-rounds of distillation
Διαθέσιμο Online:	https://www.mdpi.com/2571-5577/8/5/146
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!