Are Large Kernels Better Teachers than Transformers for ConvNets?
Tianjin HuangLu YinZhenyu ZhangLi ShenMeng FangMykola PechenizkiyZhangyang WangShiwei LiuPublished in: ICML (2023)
Keyphrases
- feed forward
- professional development
- learning environment
- learning process
- back propagation
- e learning
- learning scenarios
- kernel function
- neural network
- high school
- feature space
- technology enhanced
- learning analytics
- pre service
- support vector
- student learning
- high school students
- artificial neural networks
- authoring tool
- science education
- teaching materials
- genetic algorithm
- preservice teachers
- partial discharge
- multiple kernel learning
- kernel methods
- learning design
- concept maps
- teaching methods
- elementary school
- secondary school
- distance learning
- online learning
- mathematics education
- high voltage
- expert systems
- young students