Unverified50% confidenceFactExact time
The second model's architecture is expanded to 784→40→40→10, MSE is replaced with cross-entropy, softmax is added to the output layer, the optimizer remains plain gradient descent, and the accuracy is about 96% after 2000 epochs.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe first model uses the original MNIST dataset, with an architecture of 784→20→20→10, MSE as the loss function, plain gradient descent as the optimizer, no activation function in the output layer, and a test accuracy of about 92% after 2000 epochs of training.76% similarUnverifiedThe same scaffold raised the weak model's execution quality from 0.88 to 2.0 (across four scoring dimensions), yet pushed the strong model toward overcautious shutdown (all four dimensions dropped).73% similarUnverifiedDistilBERT retains approximately 97% of the original model's performance on the GLUE benchmark, with inference speed improved by approximately 60% and model size reduced by 40%.70% similarUnverified任务的输出熵越低（答案越可预测），推测性解码的加速效益越显著；GSM8K接受率从位置0的0.92衰减至0.53，MTBench从0.78急跌至0.1368% similarUnverifiedThe third model uses the Arabic Digits MNIST dataset, with an architecture of 784→20→20→15→10, cross-entropy loss plus plain gradient descent, an accuracy of about 96% after 2000 epochs, and uses JAX automatic differentiation to compute gradients.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1126395API
curl https://kongchang.com/api/v1/knowledge/claims/1126395MCP
get_claim(id=1126395)