主题主要有聚类，稀疏编码，局限玻尔兹曼机和深度信念网络。
Topics include clustering, sparse coding, autoencoders, restricted Boltzmann machines, and deep belief networks.
我们修改基于特征的增量编码模型，根据稀疏编码原理，将其扩展成层次结构，并利用高斯金字塔解决尺度问题。
We expand it into two-layer structure based on sparse coding theory, and use Gaus-sian pyramid to solve scale problems.
利用场景的稀疏性，将阈值以上的像素映射到三元组，对其灰度和位置信息分别熵编码；
Using the sparsity of the scene, pixels above the threshold were mapped to a triple before entropy encoding for both grayscales and locations.
LDPC码是一种特殊的具有稀疏校验矩阵的纠错编码，其性能逼近香农限。
Low density parity check (LDPC) code, which is a special case of error correction code with sparse parity-check matrix, has the performance very close to the Shannon Limit.
LDPC码是一种特殊的具有稀疏校验矩阵的纠错编码，其性能逼近香农限。
Low density parity check (LDPC) code, which is a special case of error correction code with sparse parity-check matrix, has the performance very close to the Shannon Limit.
应用推荐