Search

Deep neural networks have made significant progress in the field of computer vision. Recent studies have shown that depth, width and shortcut connections of neural network architectures play a crucial role in their performance. One of the most advanced neural network architectures, DenseNet, has achieved excellent convergence rates through dense connections. However, it still has obvious shortcomings in the usage of amount of memory. In this paper, we introduce a new type of pruning tool, threshold, which refers to the principle of the threshold voltage in MOSFET. This work employs this method to connect blocks of different depths in different ways to reduce the usage of memory. It is denoted as ThresholdNet. We evaluate ThresholdNet and other different networks on datasets of CIFAR10. Experiments show that HarDNet is twice as fast as DenseNet, and on this basis, ThresholdNet is 10% faster and 10% lower error rate than HarDNet., Comment: 5 pages, 3 figures, TAAI 2021

We revisit the satisfiability problem for two-variable logic, denoted by SAT(FO2), which is known to be NEXP-complete. The upper bound is usually derived from its well known Exponential Size Model (ESM) property. Whether it can be determinized efficiently is still an open question. In this paper we present a different approach by reducing it to a novel graph-theoretic problem that we call Conditional Independent Set (CIS). We show that CIS is NP-complete and present two simple algorithms for it with run time O(1.4423^n) and O(1.6181^n), where n is the number of vertices in the graph. We also show that unless the "Strong Exponential Time Hypothesis" (SETH) fails, there is no algorithm for CIS with run time O(1.4141^n). We show that without the equality predicate SAT(FO2) is in fact equivalent to CIS in succinct representation. This yields two algorithms for SAT(FO2) without the equality predicate with run time O(1.4423^{2^n}) and O(1.6181^{2^n}), where n is the number of predicates. To the best of our knowledge, these are the first exact algorithms for an NEXP-complete decidable logic with run time significantly lower than O(2^{2^n}). We also identify a few lower complexity fragments of FO2 which correspond to the tractable fragments of CIS. Similar to CIS, unless SETH fails, there is no algorithm for SAT(FO2) with run time O(1.4141^{2^n}). For the fragment with the equality predicate, we present a linear time many-one reduction to the fragment without the equality predicate. The reduction yields equi-satisfiable formulas with a small constant blow-up in the number of predicates. Finally, we also perform some small experiments which show that our approach is indeed more promising than the existing method (based on the ESM property). The experiments also show that although theoretically it has the worse run time, the second algorithm in general performs better than the first one.

This paper proposes a construction of $C^r$ conforming finite element spaces with arbitrary $r$ in any dimension. It is shown that if $k \ge 2^{d}r+1$ the space $\mathcal P_k$ of polynomials of degree $\le k$ can be taken as the shape function space of $C^r$ finite element spaces in $d$ dimensions. This is the first work on constructing such $C^r$ conforming finite elements in any dimension in a unified way. It solves a long-standing open problem in finite element methods., Comment: 25 pages, 5 figures

As an application in circuit quantum electrodynamics (cQED) coupled systems, superconducting resonators play an important role in high-sensitivity measurements in a superconductingsemiconductor hybrid architecture. Taking advantage of a high-impedance NbTiN resonator, we perform excited-state spectroscopy on a GaAs double quantum dot (DQD) by applying voltage pulses to one gate electrode. The pulse train modulates the DQD energy detuning and gives rise to charge state transitions at zero detuning. Benefiting from the outstanding sensitivity of the resonator, we distinguish different spin-state transitions in the energy spectrum according to the Pauli exclusion principle. Furthermore, we experimentally study how the interdot tunneling rate modifies the resonator response. The experimental results are consistent with the simulated spectra based on our model., Comment: 7 pages, 4 figures

Open intent classification is a challenging task in dialogue systems. On the one hand, it should ensure the quality of known intent identification. On the other hand, it needs to detect the open (unknown) intent without prior knowledge. Current models are limited in finding the appropriate decision boundary to balance the performances of both known intents and the open intent. In this paper, we propose a post-processing method to learn the adaptive decision boundary (ADB) for open intent classification. We first utilize the labeled known intent samples to pre-train the model. Then, we automatically learn the adaptive spherical decision boundary for each known class with the aid of well-trained features. Specifically, we propose a new loss function to balance both the empirical risk and the open space risk. Our method does not need open intent samples and is free from modifying the model architecture. Moreover, our approach is surprisingly insensitive with less labeled data and fewer known intents. Extensive experiments on three benchmark datasets show that our method yields significant improvements compared with the state-of-the-art methods. The codes are released at https://github.com/thuiar/Adaptive-Decision-Boundary., Comment: Accepted by AAAI 2021 (Main Track, Long Paper)

Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. They also have difficulties in providing high-quality supervised signals to learn clustering-friendly features for grouping unlabeled intents. In this work, we propose an effective method, Deep Aligned Clustering, to discover new intents with the aid of the limited known intent data. Firstly, we leverage a few labeled known intent samples as prior knowledge to pre-train the model. Then, we perform k-means to produce cluster assignments as pseudo-labels. Moreover, we propose an alignment strategy to tackle the label inconsistency problem during clustering assignments. Finally, we learn the intent representations under the supervision of the aligned pseudo-labels. With an unknown number of new intents, we predict the number of intent categories by eliminating low-confidence intent-wise clusters. Extensive experiments on two benchmark datasets show that our method is more robust and achieves substantial improvements over the state-of-the-art methods. The codes are released at https://github.com/thuiar/DeepAligned-Clustering., Comment: Accepted by AAAI 2021 (Main Track, Long Paper)

We perform Floquet spectroscopy in a GaAs double quantum dot system coupled to a high-impedance superconducting resonator. By applying microwave induced consecutive passages under a double resonance condition, we observe novel Landau-Zener-St\"uckelberg-Majorana interference patterns that stem from a cavity-assisted interference pattern modified by the depletion of the ground state. Our experimental results reveal the stationary state behavior of a strongly driven two-level system, and are consistent with the simulations based on our theoretical model. This study provides an excellent platform for investigating the dynamics of Floquet states in the presence of strong driving., Comment: 10 pages, 7 figures

In this paper, we propose a two-stage ranking approach for recommending linear TV programs. The proposed approach first leverages user viewing patterns regarding time and TV channels to identify potential candidates for recommendation and then further leverages user preferences to rank these candidates given textual information about programs. To evaluate the method, we conduct empirical studies on a real-world TV dataset, the results of which demonstrate the superior performance of our model in terms of both recommendation accuracy and time efficiency., Comment: 8 pages

With the maturity and popularity of dialogue systems, detecting user's unknown intent in dialogue systems has become an important task. It is also one of the most challenging tasks since we can hardly get examples, prior knowledge or the exact numbers of unknown intents. In this paper, we propose SofterMax and deep novelty detection (SMDN), a simple yet effective post-processing method for detecting unknown intent in dialogue systems based on pre-trained deep neural network classifiers. Our method can be flexibly applied on top of any classifiers trained in deep neural networks without changing the model architecture. We calibrate the confidence of the softmax outputs to compute the calibrated confidence score (i.e., SofterMax) and use it to calculate the decision boundary for unknown intent detection. Furthermore, we feed the feature representations learned by the deep neural networks into traditional novelty detection algorithm to detect unknown intents from different perspectives. Finally, we combine the methods above to perform the joint prediction. Our method classifies examples that differ from known intents as unknown and does not require any examples or prior knowledge of it. We have conducted extensive experiments on three benchmark dialogue datasets. The results show that our method can yield significant improvements compared with the state-of-the-art baselines, Comment: Published in Knowledge-Based Systems 2019

We develop a new spectroscopic method to quickly and intuitively characterize the coupling of two microwave-photon-coupled semiconductor qubits via a high-impedance resonator. Highly distinctive and unique geometric patterns are revealed as we tune the qubit tunnel couplings relative to the frequency of the mediating photons. These patterns are in excellent agreement with a simulation using the Tavis-Cummings model, and allow us to readily identify different parameter regimes for both qubits in the detuning space. This method could potentially be an important component in the overall spectroscopic toolbox for quickly characterizing certain collective properties of multiple cavity QED coupled qubits., Comment: 13 pages, 4 figures

We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for universal approximation using continuous-time deep residual networks, which can also be understood as approximation theories in $L^p$ using flow maps of dynamical systems. In specific cases, rates of approximation in terms of the time horizon are also established. Overall, these results reveal that composition function approximation through flow maps present a new paradigm in approximation theory and contributes to building a useful mathematical framework to investigate deep learning., Comment: Revision 1