Network architecture of DeepGAM.

<p>( <b>a</b>) Each feature passes through a Straight-Through Estimator (STE), which learns to select relevant features during training. The selected feature <i>z</i><sub><i>j</i></sub> is then fed into a 3-layer neural network <i>f</i&g...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Chiyoung Lee (11782395) (author)
مؤلفون آخرون: Yeri Kim (21539075) (author), Seoyoung Kim (2603596) (author), Mary Whooley (6090683) (author), Heewon Kim (7498565) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
الوصف
الملخص:<p>( <b>a</b>) Each feature passes through a Straight-Through Estimator (STE), which learns to select relevant features during training. The selected feature <i>z</i><sub><i>j</i></sub> is then fed into a 3-layer neural network <i>f</i>, and and its output is combined with a learnable bias parameter to represent the depression status. ( <b>b</b>) The STE selects a feature by multiplying it with a binary value in the forward pass, and enables parameter <i>ϕ</i> to be updated via gradient descent by omitting the non-differentiable round function in the backward pass. ( <b>c</b>) The 3-layer neural network consists of Fully Connected (FC) layers with ReLU and tanh activations. Each feature has distinct learnable parameters <i>ϕ</i> and .</p>