Do we really need encoders for generative models?
In modern generative AI, encoders are commonly used during training to help models understand the context of input data. However, these encoders are often removed during inference. This raises an interesting question, if we train models using only decoders, can they still generate meaningful outputs?
529 个字词
|
3 分钟
Kronecker Product
克劳内克积(Kronecker Product)是两个矩阵的乘积,结果是一个新的矩阵,其元素是原矩阵元素的乘积。对于两个矩阵 A 和 B,其克劳内克积记作 A \otimes B。常用于信号处理、图像处理等领域。也叫做张量积或直积。
765 个字词
|
4 分钟
Fourier and Wavelets for Deep Learning
令 f\in L^2(\mathbb{R})。傅里叶变换(在 L^2 意义下)把信号表示为全局正弦基的叠加:
3373 个字词
|
17 分钟
Collections
Tech Notes
Be a big fan of rising technologies.
Algorithm Notes
Woo. Time-tested wisdom.
强化学习合集
Notes on reading papers in the field of reinforcement learning.
Maths Laboratory
Do mathematics have a lab as well? Absolutely, with computer simulations.
生成式模型合集
Generative Models, modeling complex data distributions.
Tags

