This paper presents a 6.8-GHz compact digital fractional-N PLL based on a pulse-shaped loop filter, enabling a loop bandwidth of$0.26f_{ref}$to suppress the ring oscillator’s phase noise. It leverages a constant-slope DTC with range extension technique to save 50% area of the capacitor array. The embedded nonlinearity cancellation and digital offset compensation further improve the spectrum purity. Fabricated in a 28-nm CMOS process, the pulse-shaper-based PLL occupies$\text {0.025mm}^{{2}}$core area, achieves an integrated jitter of 804 fs and −53.2 dBc fractional spur at near-integer channels with a power consumption of 5.68mW, obtaining a$\text {FoM}_{\text {Jitter-N-Area}}$of −269.9 dB.

This paper presents a power-efficient constant-slope digital-to-time converter (DTC) with embedded nonlinearity cancellation. By utilizing the capacitor based digital-to-analog converter (C-DAC) to adjust the initial voltage of the discharging process, the DTC achieves a fine resolution of$\mu \text{W}$at 50-MHz clock rate. It achieves a fine resolution of 563-fs over a 10-bit range. The measured differential nonlinearity (DNL) and integral nonlinearity (INL) are 0.14/0.96-LSB, respectively.

In this paper, we present the mQA model, which is able to answer questions about the content of an image. The answer can be a sentence, a phrase or a single word. Our model contains four components: a Long Short-Term Memory (LSTM) to extract the question representation, a Convolutional Neural Network (CNN) to extract the visual representation, an LSTM for storing the linguistic context in an answer, and a fusing component to combine the information from the first three components and generate the answer. We construct a Freestyle Multilingual Image Question Answering (FM-IQA) dataset to train and evaluate our mQA model. It contains over 150,000 images and 310,000 freestyle Chinese question-answer pairs and their English translations. The quality of the generated answers of our mQA model on this dataset is evaluated by human judges through a Turing Test. Specifically, we mix the answers provided by humans and our model. The human judges need to distinguish our model from the human. They will also provide a score (i.e. 0, 1, 2, the larger the better) indicating the quality of the answer. We propose strategies to monitor the quality of this evaluation process. The experiments show that in 64.7% of cases, the human judges cannot distinguish our model from humans. The average score is 1.454 (1.918 for human). The details of this work, including the FM-IQA dataset, can be found on the project page: \url{http://idl.baidu.com/FM-IQA.html}.

Constructing a good graph to represent data structures is critical for many important machine learning tasks such as clustering and classification. This paper proposes a novel non-negative low-rank and sparse (NNLRS) graph for semi-supervised learning. The weights of edges in the graph are obtained by seeking a nonnegative low-rank and sparse matrix that represents each data sample as a linear combination of others. The so-obtained NNLRS-graph can capture both the global mixture of subspaces structure (by the low rankness) and the locally linear structure (by the sparseness) of the data, hence is both generative and discriminative. We demonstrate the effectiveness of NNLRS-graph in semi-supervised classification and discriminative analysis. Extensive experiments testify to the significant advantages of NNLRS-graph over graphs obtained through conventional means.

Semi-supervised dimensionality reduction is very important in mining high-dimensional data due to the lack of costly labeled data. This paper studies the Semi-supervised Discriminant Analysis (SDA) algorithm, which aims at dimensionality reduction utilizing both limited labeled data and abundant unlabeled data. Different from other relative work, we pay our attention to graph construction, which plays a key role in graph based SSL methods. Inspired by the advances of compressive sensing, we propose a novel graph construction method via group sparsity, which means to constrain the reconstruct data to be sparse for each sample, and constrain the representation in each class to be quite similar. Experimental results show that our method can significantly improve the performance of SDA, and outperform state-of-the-art methods.

Graph plays a very important role in graph based semi-supervised learning (SSL) methods. However, most current graph construction methods emphasize on local properties of the graph. In this paper, inspired by the advances of compressive sensing, we present a novel method to construct a so-called low-rank graph (LR-graph) for graph based SSL methods. Assuming that the graph is sparse and low rank, our proposed method uses both the local property and the global property of the graph, and thus is better at capturing the global structure of all data. Compared with current graphs, LR-graph is more informative and discriminative, and robust to outliers. Experiments on generic object recognition show that LR-graph achieves state-of-the-art performance for graph based SSL methods.