2 code implementations • 24 Apr 2020 • Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Hassan Ghasemzadeh
However, it is more reliable to preserve the knowledge it has learned from the previous tasks.
3 code implementations • 9 Feb 2019 • Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Ang Li, Nir Levine, Akihiro Matsukawa, Hassan Ghasemzadeh
To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher.