Unverified50% confidenceFactExact time
The course's A0 assignment requires students to manually implement a linear layer, including explicitly saving the forward input and manually computing backpropagation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedThis experiment adopts trajectory-level distillation, which belongs to the category of behavioral cloning, directly having the student model imitate the external behavioral sequences of the teacher model.69% similarUnverifiedA project implementing linear regression from scratch using NumPy connects calculus, linear algebra, and programming, helping one understand the effect of gradient descent and learning rate on convergence.68% similarUnverifiedStéphane Ross等人提出DAgger算法，通过训练中持续让学生模型产生新轨迹并请求教师标注来缓解行为克隆的分布偏移问题67% similarUnverified知识蒸馏的中间层对齐策略（如PKD、TinyBERT）通过强制学生模型的隐藏表示模仿教师模型的分布间接约束嵌入几何结构65% similarUnverified模仿学习的经典算法包括行为克隆（Behavioral Cloning）和逆强化学习（IRL），DAgger是介于两者之间的折中方法64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/896504API
curl https://kongchang.com/api/v1/knowledge/claims/896504MCP
get_claim(id=896504)