Deep learning has unlocked new paths towards the emulation of the peculiarly-human capability of learning from examples. While this kind of bottom-up learning works well for tasks such as image classification or object detection, it is not as effective when it comes to natural language processing. Communication is much more than learning a sequence of letters and words: it requires a basic understanding of the world and social norms, cultural awareness, commonsense knowledge, etc.; all things that we mostly learn in a top-down manner. In this work, we integrate top-down and bottom-up learning via an ensemble of symbolic and subsymbolic AI tools, which we apply to the interesting problem of polarity detection from text. In particular, we integrate logical reasoning within deep learning architectures to build a new version of Sentic-Net, a commonsense knowledge base for sentiment analysis.

Inking and gesturing are two central tasks in pen-based user interfaces. Switching between modes for entry of uninterpreted ink and entry of gestures is required by many pen-based user interfaces. Without an appropriate mode switching technique, pen-based interactions in such situations may be inefficient and cumbersome. In this paper, we investigate five techniques for switching between ink and gesture modes in pen interfaces, including a penpressure based mode switching technique that allows implicit mode transition. A quantitative experimental study was conducted to evaluate the performance of these techniques. The results suggest that pressing a button with the non-preferred hand offers the fastest performance, while the technique of holding the pen still is significantly slower and more prone to error than the other techniques. Pressure, while promising, did not perform as well as the non-preferred hand button with our current implementation.

No abstract

No abstract

No abstract

Semi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning. The majority of existing semi-supervised VAEs utilize a classifier to exploit label information, where the parameters of the classifier are introduced to the VAE. Given the limited labeled data, learning the parameters for the classifiers may not be an optimal solution for exploiting label information. Therefore, in this paper, we develop a novel approach for semi-supervised VAE without classifier. Specifically, we propose a new model called Semi-supervised Disentangled VAE (SDVAE), which encodes the input data into disentangled representation and non-interpretable representation, then the category information is directly utilized to regularize the disentangled representation via the equality constraint. To further enhance the feature learning ability of the proposed VAE, we incorporate reinforcement learning to relieve the lack of data. The dynamic framework is capable of dealing with both image and text data with its corresponding encoder and decoder networks. Extensive experiments on image and text datasets demonstrate the effectiveness of the proposed framework.

No abstract

No abstract