Abstract: The present invention relates to the technical field of integrated circuits. Disclosed is a one-time programmable memory with a high reliability and a low reading voltage, comprising: a first MOS transistor, a second MOS transistor, and an antifuse component. A gate terminal of the first MOS transistor is connected to a second connecting line (WS), a first connection terminal of the first MOS transistor is connected to the antifuse component, the antifuse component is connected to a first connecting line (WP), and a second connection terminal of the first MOS transistor is connected to a third connecting line (BL). A first connection terminal of the second MOS transistor is connected to a fourth connecting line (BR), and a second connection terminal of the second MOS transistor is connected to a third connecting line (BL). The invention further comprises a voltage limiting device with a control terminal and two connection terminals.

Abstract: Presented herein are embodiments of a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions. In embodiments, it directly models the probability distribution of generating a word given a previous word or words and an image, and image captions are generated according to this distribution. In embodiments, the model comprises two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. In embodiments, these two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of an embodiment of model was validated on four benchmark datasets, and it outperformed the state-of-the-art methods. In embodiments, the m-RNN model may also be applied to retrieval tasks for retrieving images or captions.

Abstract: Described herein are systems and methods that address the task of learning novel visual concepts, and their interactions with other concepts, from a few images with sentence descriptions. Using linguistic context and visual features, embodiments are able to efficiently hypothesize the semantic meaning of new words and add them to model word dictionaries so that they can be used to describe images which contain these novel concepts. In the experiments, it was shown that the tested embodiments effectively learned novel visual concepts from a few examples without disturbing the previously learned concepts.

Abstract: Presented herein are embodiments of a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions. In embodiments, it directly models the probability distribution of generating a word given a previous word or words and an image, and image captions are generated according to this distribution. In embodiments, the model comprises two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. In embodiments, these two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of an embodiment of model was validated on four benchmark datasets, and it outperformed the state-of-the-art methods. In embodiments, the m-RNN model may also be applied to retrieval tasks for retrieving images or captions.

Abstract: Embodiments of a multimodal question answering (mQA) system are presented to answer a question about the content of an image. In embodiments, the model comprises four components: a Long Short-Term Memory (LSTM) component to extract the question representation; a Convolutional Neural Network (CNN) component to extract the visual representation; an LSTM component 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. A Freestyle Multilingual Image Question Answering (FM-IQA) dataset was constructed to train and evaluate embodiments of the mQA model. The quality of the generated answers of the mQA model on this dataset is evaluated by human judges through a Turing Test.

Abstract: A high-voltage-resistant rectifier with standard CMOS transistors is disclosed in present invention. In a bridge full-wave rectifier comprising four MOS transistors, extra transistors are connected in series between the transistors which endure high voltage and the input to decrease the voltage imposed on the gate of them; moreover, the present invention provides a way to divide voltage imposed between the gate and the source of the said transistors by connecting in series with extra transistors, so it is achieved to implement a high-voltage-resistant rectifier with standard low voltage CMOS transistors without additional process complexity, and decreases manufacture and process costs.

Abstract: A high-voltage-resistant rectifier with standard CMOS transistors is disclosed in present invention. In a bridge full-wave rectifier comprising four MOS transistors, extra transistors are connected in series between the transistors which endure high voltage and the input to decrease the voltage imposed on the gate of them; moreover, the present invention provides a way to divide voltage imposed between the gate and the source of the said transistors by connecting in series with extra transistors, so it is achieved to implement a high-voltage-resistant rectifier with standard low voltage CMOS transistors without additional process complexity, and decreases manufacture and process costs.