You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In your paper, you mention "black-box" 13 times and "black-box function evaluations" 8 times without providing description about them. And it is also listed as one contribution of your paper, could you help to elaborate about this?
The text was updated successfully, but these errors were encountered:
black-box function evaluations refers to input-output examples of mathematical functions when the function is treated as a "black-box". To be more clear the input-output pair ($\pi/2$, 1) is a an evaluation for the sine function. Sine is treated as a black-box because we do not care how we got the pair ($\pi/2$, 1), we just use the pair as a black-box evaluation for the function. We use a few such pairs for all the mathematical functions and combine them with the symbolic representation of the functions (e.g. sin^2(x)+cos^2(x)=1).
@ForoughA Really thanks for your detailed explanations. Personally, I really like your solid works on building structural models. By the way, I am still confused about the "function evaluation expressions" part. you claim that this is auto-encoder, but from your figure 1(b), I only see this is more similar to siamse network not autoencoder. Also, you mention that $W^-1_{num}$ is the decoder params, does this matrix used to transform "dense embedding into scalar"?. Why not directly do "vector-vecctor product" to calculate the cos similarity?
In your paper, you mention "black-box" 13 times and "black-box function evaluations" 8 times without providing description about them. And it is also listed as one contribution of your paper, could you help to elaborate about this?
The text was updated successfully, but these errors were encountered: