DropConnect is a recently introduced algorithm to prevent the co-adaptation of feature detectors. Compared to Dropout, DropConnect gains state-of-the-art results on several image recognition benchmarks. Motivated by the success of DropConnect, we extended this algorithm with the ability of sparse feature selection. In DropConnect algorithm, the dropping masks of weights are generated using Bernoulli gating variables that are independent of the weights and activations. We introduce a new strategy to generate masks depending on the outputs of previous layer. Using this method, neurons which are promising to produce sparser features will be assigned a bigger possibility to keep active in the forward and backward propagations. We then evaluate such sparsity constrained DropConnect on MNIST and CIFAR datasets in comparison with ordinary DropConnect and Dropout method. The results show that our new method improves the sparsity of features significantly, while not degrading the precision.

MRI of effective transverse relaxation rate (R2*) measurement is a reliable method for liver iron concentration quantification. However, R2* mapping can be degraded by noise, especially in the case of iron overload. This study aimed to develop a deep learning method for MRI R2* relaxometry of an iron-loaded liver using a two-stage cascaded neural network. The proposed method, named CadamNet, combines two convolutional neural networks separately designed for image denoising and parameter mapping into a cascade framework, and the physics-based R2* decay model was incorporated in training the mapping network to enforce data consistency further. CadamNet was trained using simulated liver data with Rician noise, which was constructed from clinical liver data. The performance of CadamNet was quantitatively evaluated on simulated data with varying noise levels as well as clinical liver data and compared with the single-stage parameter mapping network (MappingNet) and two conventional model-based R2* mapping methods. CadamNet consistently achieved high-quality R2* maps and outperformed MappingNet at varying noise levels. Compared with conventional R2* mapping methods, CadamNet yielded R2* maps with lower errors, higher quality, and substantially increased efficiency. In conclusion, the proposed CadamNet enables accurate and efficient iron-loaded liver R2* mapping, especially in the presence of severe noise.

Image recognition, especially traffic sign recognition is an important task for autonomous driving and driver assistance systems. A new Convolutional Neural Network model with the ability of feature selection in frequency domain is presented in this paper, called Frequency Selective Filter Aided (FSFA) CNN model. The new model can integrate low-pass and high-pass filters into both forward and backward propagations in order to place special emphases on feature components in different frequency bands. The theoretical basis, as well as forward and backward propagations are also formulated. Experiments on CIFAR and GTSRB traffic sign recognition datasets show that the proposed model yields better performance for the task of image recognition compared with classic methods.