Sharif Digital Repository

In this paper, a novel multi-head multi-layer perceptron (MLP) structure is presented for implicit neural representation (INR). Since conventional rectified linear unit (ReLU) networks are shown to exhibit spectral bias towards learning low-frequency features of the signal, we aim at mitigating this defect by taking advantage of local structure of the signals. To be more specific, an MLP is used to capture the global features of the underlying generator function of the desired signal. Then, several heads are utilized to reconstruct disjoint local features of the signal, and to reduce the computational complexity, sparse layers are deployed for attaching heads to the body. Through various... 

Recent research has revealed that the security of deep neural networks that directly process 3D point clouds to classify objects can be threatened by adversarial samples. Al-though existing adversarial attack methods achieve high success rates, they do not restrict the point modifications enough to preserve the point cloud appearance. To overcome this shortcoming, two constraints are proposed. These include applying hard boundary constraints on the number of modified points and on the point perturbation norms. Due to the restrictive nature of the problem, the search space contains many local maxima. The proposed method addresses this issue by using a high step-size at the beginning of the... 

The current study investigates the effect of polyacrylonitrile (PAN) addition on morphology and antifouling properties of poly(vinyl chloride) (PVC) asymmetric flat ultrafiltration (UF) membranes. The membranes are prepared via phase inversion method induced by immersion precipitation at different PVC/PAN blending ratio up to 40 wt% PAN. Also, membranes with blending ratio of PVC/ PAN:70/30, which showed the highest water flux and flux recovery ratio, were used for membrane preparation with 4 wt% of Polyethylene glycol (PEG) addition in four different molecular weight, 600 Da, 1,000 Da, 6,000 Da and 20,000 Da, which was used as pore former and hydrophilic polymeric additive. The performance... 

Detecting emotions directly from a speech signal plays an important role in effective human-computer interactions. Existing speech emotion recognition models require massive computational and storage resources, making them hard to implement concurrently with other machine-interactive tasks in embedded systems. In this paper, we propose an efficient and lightweight fully convolutional neural network for speech emotion recognition in systems with limited hardware resources. In the proposed FCNN model, various feature maps are extracted via three parallel paths with different filter sizes. This helps deep convolution blocks to extract high-level features, while ensuring sufficient separability....