Nowadays, deep neural networks are widely used in mission critical systems such as healthcare, self-driving vehicles, and military which have direct impact on human lives. However, the black-box nature of deep neural networks challenges its use in mission critical applications, raising ethical and judicial concerns inducing lack of trust. Explainable Artificial Intelligence (XAI) is a field of Artificial Intelligence (AI) that promotes a set of tools, techniques, and algorithms that can generate high-quality interpretable, intuitive, human-understandable explanations of AI decisions. In addition to providing a holistic view of the current XAI landscape in deep learning, this paper provides mathematical summaries of seminal work. We start by proposing a taxonomy and categorizing the XAI techniques based on their scope of explanations, methodology behind the algorithms, and explanation level or usage which helps build trustworthy, interpretable, and self-explanatory deep learning models. We then describe the main principles used in XAI research and present the historical timeline for landmark studies in XAI from 2007 to 2020. After explaining each category of algorithms and approaches in detail, we then evaluate the explanation maps generated by eight XAI algorithms on image data, discuss the limitations of this approach, and provide potential future directions to improve XAI evaluation.

This paper focuses on convolution neural network quantization problem. The quantization has a distinct stage of data conversion from floating-point into integer-point numbers. In general, the process of quantization is associated with the reduction of the matrix dimension via limited precision of the numbers. However, the training and inference stages of deep learning neural network are limited by the space of the memory and a variety of factors including programming complexity and even reliability of the system. On the whole the process of quantization becomes more and more popular due to significant impact on performance and minimal accuracy loss. Various techniques for networks quantization have been already proposed, including quantization aware training and integer arithmetic-only inference. Yet, a detailed comparison of various quantization configurations, combining all proposed methods haven't been presented yet. This comparison is important to understand selection of quantization hyperparameters during training to optimize networks for inference while preserving their robustness. In this work, we perform in-depth analysis of parameters in the quantization aware training, the process of simulating precision loss in the forward pass by quantizing and dequantizing tensors. Specifically, we modify rounding modes, input preprocessing, output data signedness, bitwidth of the quantization and locations of precision loss simulation to evaluate how they affect accuracy of deep neural network aimed at performing efficient calculations on resource-constrained devices.

Deep feature learning methods have been aggressively applied in the field of music tagging retrieval Genre categorization, mood classification, and chord detection are the most common tags from local spectral to temporal structure. Convolutional Neural networks (CNNs) using kernels extract the local features that are in different levels of hierarchy while Recurrent Neural Networks (RNNs) discover the global features to understand the temporal context, CRNN architectures as a powerful music tagging utilize the benefits of the both CNN and RNN structures. In this article a CRNN structure on MagnaTagA Tune dataset is proposed. The AUC-ROC index for the proposed architecture is 0.893 which shows its superiority rather than traditional structures on the same database. The merging mechanism to obtain 50 tags from the whole 188 existing tags of this dataset and simple CRNN architecture designed for tag discovering are the main contribution of this paper.