Spiking neural networks (SNNs) are the third generation of neural networks and can explore both rate and temporal coding for energy-efficient event-driven computation. However, the decision accuracy of existing SNN designs is contingent upon processing a large number of spikes over a long period. Nevertheless, the switching power of SNN hardware accelerators is proportional to the number of spikes processed while the length of spike trains limits throughput and static power efficiency. This paper presents the first study on developing temporal compression to significantly boost throughput and reduce energy dissipation of digital hardware SNN accelerators while being applicable to multiple spike codes. The proposed compression architectures consist of low-cost input spike compression units, novel input-and-output-weighted spiking neurons, and reconfigurable time constant scaling to support large and flexible time compression ratios. Our compression architectures can be transparently applied to any given pre-designed SNNs employing either rate or temporal codes while incurring minimal modification of the neural models, learning algorithms, and hardware design. Using spiking speech and image recognition datasets, we demonstrate the feasibility of supporting large time compression ratios of up to 16x, delivering up to 15.93x, 13.88x, and 86.21x improvements in throughput, energy dissipation, the tradeoffs between hardware area, runtime, energy, and classification accuracy, respectively based on different spike codes on a Xilinx Zynq-7000 FPGA. These results are achieved while incurring little extra hardware overhead.
Deep learning has achieved spectacular performance in image and speech recognition and synthesis. It outperforms other machine learning algorithms in problems where large amounts of data are available. In the area of measurement technology, instruments based on the Photonic Time Stretch have established record real-time measurement throughput in spectroscopy, optical coherence tomography, and imaging flow cytometry. These extreme-throughput instruments generate approximately 1 Tbit/s of continuous measurement data and have led to the discovery of rare phenomena in nonlinear and complex systems as well as new types of biomedical instruments. Owing to the abundance of data they generate, time stretch instruments are a natural fit to deep learning classification. Previously we had shown that high-throughput label-free cell classification with high accuracy can be achieved through a combination of time stretch microscopy, image processing and feature extraction, followed by deep learning for finding cancer cells in the blood. Such a technology holds promise for early detection of primary cancer or metastasis. Here we describe a new implementation of deep learning which entirely avoids the computationally costly image processing and feature extraction pipeline. The improvement in computational efficiency makes this new technology suitable for cell sorting via deep learning. Our neural network takes less than a millisecond to classify the cells, fast enough to provide a decision to a cell sorter. We demonstrate the applicability of our new method in the classification of OT-II white blood cells and SW-480 epithelial cancer cells with more than 95\% accuracy in a label-free fashion.
Deep learning (DL) has recently achieved tremendous success in a variety of cutting-edge applications, e.g., image recognition, speech and natural language processing, and autonomous driving. Besides the available big data and hardware evolution, DL frameworks and platforms play a key role to catalyze the research, development, and deployment of DL intelligent solutions. However, the difference in computation paradigm, architecture design and implementation of existing DL frameworks and platforms brings challenges for DL software development, deployment, maintenance, and migration. Up to the present, it still lacks a comprehensive study on how current diverse DL frameworks and platforms influence the DL software development process. In this paper, we initiate the first step towards the investigation on how existing state-of-the-art DL frameworks (i.e., TensorFlow, Theano, and Torch) and platforms (i.e., server/desktop, web, and mobile) support the DL software development activities. We perform an in-depth and comparative evaluation on metrics such as learning accuracy, DL model size, robustness, and performance, on state-of-the-art DL frameworks across platforms using two popular datasets MNIST and CIFAR-10. Our study reveals that existing DL frameworks still suffer from compatibility issues, which becomes even more severe when it comes to different platforms. We pinpoint the current challenges and opportunities towards developing high quality and compatible DL systems. To ignite further investigation along this direction to address urgent industrial demands of intelligent solutions, we make all of our assembled feasible toolchain and dataset publicly available.
As one of the fundamental tasks in text analysis, phrase mining aims at extracting quality phrases from a text corpus. Phrase mining is important in various tasks such as information extraction/retrieval, taxonomy construction, and topic modeling. Most existing methods rely on complex, trained linguistic analyzers, and thus likely have unsatisfactory performance on text corpora of new domains and genres without extra but expensive adaption. Recently, a few data-driven methods have been developed successfully for extraction of phrases from massive domain-specific text. However, none of the state-of-the-art models is fully automated because they require human experts for designing rules or labeling phrases. Since one can easily obtain many quality phrases from public knowledge bases to a scale that is much larger than that produced by human experts, in this paper, we propose a novel framework for automated phrase mining, AutoPhrase, which leverages this large amount of high-quality phrases in an effective way and achieves better performance compared to limited human labeled phrases. In addition, we develop a POS-guided phrasal segmentation model, which incorporates the shallow syntactic information in part-of-speech (POS) tags to further enhance the performance, when a POS tagger is available. Note that, AutoPhrase can support any language as long as a general knowledge base (e.g., Wikipedia) in that language is available, while benefiting from, but not requiring, a POS tagger. Compared to the state-of-the-art methods, the new method has shown significant improvements in effectiveness on five real-world datasets across different domains and languages.
Artificial General Intelligence is a field of research aiming to distill the principles of intelligence that operate independently of a specific problem domain or a predefined context and utilize these principles in order to synthesize systems capable of performing any intellectual task a human being is capable of and eventually go beyond that. While "narrow" artificial intelligence which focuses on solving specific problems such as speech recognition, text comprehension, visual pattern recognition, robotic motion, etc. has shown quite a few impressive breakthroughs lately, understanding general intelligence remains elusive. In the paper we offer a novel theoretical approach to understanding general intelligence. We start with a brief introduction of the current conceptual approach. Our critique exposes a number of serious limitations that are traced back to the ontological roots of the concept of intelligence. We then propose a paradigm shift from intelligence perceived as a competence of individual agents defined in relation to an a priori given problem domain or a goal, to intelligence perceived as a formative process of self-organization by which intelligent agents are individuated. We call this process open-ended intelligence. Open-ended intelligence is developed as an abstraction of the process of cognitive development so its application can be extended to general agents and systems. We introduce and discuss three facets of the idea: the philosophical concept of individuation, sense-making and the individuation of general cognitive agents. We further show how open-ended intelligence can be framed in terms of a distributed, self-organizing network of interacting elements and how such process is scalable. The framework highlights an important relation between coordination and intelligence and a new understanding of values. We conclude with a number of questions for future research.
The present phase of Machine Learning is characterized by supervised learning algorithms relying on large sets of labeled examples ($n \to \infty$). The next phase is likely to focus on algorithms capable of learning from very few labeled examples ($n \to 1$), like humans seem able to do. We propose an approach to this problem and describe the underlying theory, based on the unsupervised, automatic learning of a ``good'' representation for supervised learning, characterized by small sample complexity ($n$). We consider the case of visual object recognition though the theory applies to other domains. The starting point is the conjecture, proved in specific cases, that image representations which are invariant to translations, scaling and other transformations can considerably reduce the sample complexity of learning. We prove that an invariant and unique (discriminative) signature can be computed for each image patch, $I$, in terms of empirical distributions of the dot-products between $I$ and a set of templates stored during unsupervised learning. A module performing filtering and pooling, like the simple and complex cells described by Hubel and Wiesel, can compute such estimates. Hierarchical architectures consisting of this basic Hubel-Wiesel moduli inherit its properties of invariance, stability, and discriminability while capturing the compositional organization of the visual world in terms of wholes and parts. The theory extends existing deep learning convolutional architectures for image and speech recognition. It also suggests that the main computational goal of the ventral stream of visual cortex is to provide a hierarchical representation of new objects/images which is invariant to transformations, stable, and discriminative for recognition---and that this representation may be continuously learned in an unsupervised way during development and visual experience.
In the area of computer science focusing on creating machines that can engage on behaviors that humans consider intelligent. The ability to create intelligent machines has intrigued humans since ancient times and today with the advent of the computer and 50 years of research into various programming techniques, the dream of smart machines is becoming a reality. Researchers are creating systems which can mimic human thought, understand speech, beat the best human chessplayer, and countless other feats never before possible. Ability of the human to estimate the information is most brightly shown in using of natural languages. Using words of a natural language for valuation qualitative attributes, for example, the person pawns uncertainty in form of vagueness in itself estimations. Vague sets, vague judgments, vague conclusions takes place there and then, where and when the reasonable subject exists and also is interested in something. The vague sets theory has arisen as the answer to an illegibility of language the reasonable subject speaks. Language of a reasonable subject is generated by vague events which are created by the reason and which are operated by the mind. The theory of vague sets represents an attempt to find such approximation of vague grouping which would be more convenient, than the classical theory of sets in situations where the natural language plays a significant role. Such theory has been offered by known American mathematician Gau and Buehrer .In our paper we are describing how vagueness of linguistic variables can be solved by using the vague set theory.This paper is mainly designed for one of directions of the eventology (the theory of the random vague events), which has arisen within the limits of the probability theory and which pursue the unique purpose to describe eventologically a movement of reason.
Biological spiking neural networks (SNNs) can temporally encode information in their outputs, e.g. in the rank order in which neurons fire, whereas artificial neural networks (ANNs) conventionally do not. As a result, models of SNNs for neuromorphic computing are regarded as potentially more rapid and efficient than ANNs when dealing with temporal input. On the other hand, ANNs are simpler to train, and usually achieve superior performance. Here we show that temporal coding such as rank coding (RC) inspired by SNNs can also be applied to conventional ANNs such as LSTMs, and leads to computational savings and speedups. In our RC for ANNs, we apply backpropagation through time using the standard real-valued activations, but only from a strategically early time step of each sequential input example, decided by a threshold-crossing event. Learning then incorporates naturally also _when_ to produce an output, without other changes to the model or the algorithm. Both the forward and the backward training pass can be significantly shortened by skipping the remaining input sequence after that first event. RC-training also significantly reduces time-to-insight during inference, with a minimal decrease in accuracy. The desired speed-accuracy trade-off is tunable by varying the threshold or a regularization parameter that rewards output entropy. We demonstrate these in two toy problems of sequence classification, and in a temporally-encoded MNIST dataset where our RC model achieves 99.19% accuracy after the first input time-step, outperforming the state of the art in temporal coding with SNNs, as well as in spoken-word classification of Google Speech Commands, outperforming non-RC-trained early inference with LSTMs.
Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions. Herein, we propose Neural-Symbolic Solver (NS-Solver) to explicitly and seamlessly incorporate different levels of symbolic constraints by auxiliary tasks. Our NS-Solver consists of a problem reader to encode problems, a programmer to generate symbolic equations, and a symbolic executor to obtain answers. Along with target expression supervision, our solver is also optimized via 4 new auxiliary objectives to enforce different symbolic reasoning: a) self-supervised number prediction task predicting both number quantity and number locations; b) commonsense constant prediction task predicting what prior knowledge (e.g. how many legs a chicken has) is required; c) program consistency checker computing the semantic loss between predicted equation and target equation to ensure reasonable equation mapping; d) duality exploiting task exploiting the quasi duality between symbolic equation generation and problem's part-of-speech generation to enhance the understanding ability of a solver. Besides, to provide a more realistic and challenging benchmark for developing a universal and scalable solver, we also construct a new large-scale MWP benchmark CM17K consisting of 4 kinds of MWPs (arithmetic, one-unknown linear, one-unknown non-linear, equation set) with more than 17K samples. Extensive experiments on Math23K and our CM17k demonstrate the superiority of our NS-Solver compared to state-of-the-art methods.
Quantum machine learning (QML) can complement the growing trend of using learned models for a myriad of classification tasks, from image recognition to natural speech processing. A quantum advantage arises due to the intractability of quantum operations on a classical computer. Many datasets used in machine learning are crowd sourced or contain some private information. To the best of our knowledge, no current QML models are equipped with privacy-preserving features, which raises concerns as it is paramount that models do not expose sensitive information. Thus, privacy-preserving algorithms need to be implemented with QML. One solution is to make the machine learning algorithm differentially private, meaning the effect of a single data point on the training dataset is minimized. Differentially private machine learning models have been investigated, but differential privacy has yet to be studied in the context of QML. In this study, we develop a hybrid quantum-classical model that is trained to preserve privacy using differentially private optimization algorithm. This marks the first proof-of-principle demonstration of privacy-preserving QML. The experiments demonstrate that differentially private QML can protect user-sensitive information without diminishing model accuracy. Although the quantum model is simulated and tested on a classical computer, it demonstrates potential to be efficiently implemented on near-term quantum devices (noisy intermediate-scale quantum [NISQ]). The approach's success is illustrated via the classification of spatially classed two-dimensional datasets and a binary MNIST classification. This implementation of privacy-preserving QML will ensure confidentiality and accurate learning on NISQ technology.