Fermion sampling is to generate probability distribution of a many-body Slater-determinant wavefunction, which is termed determinantal point process in statistical analysis. For its inherently-embedded Pauli exclusion principle, its application reach
es beyond simulating fermionic quantum many-body physics to constructing machine learning models for diversified datasets. Here we propose a fermion sampling algorithm, which has a polynomial time-complexity -- quadratic in the fermion number and linear in the system size. This algorithm is about 100% more efficient in computation time than the best known algorithms. In sampling the corresponding marginal distribution, our algorithm has a more drastic improvement, achieving a scaling advantage. We demonstrate its power on several test applications, including sampling fermions in a many-body system and a machine learning task of text summarization, and confirm its improved computation efficiency over other methods by counting floating-point operations.
Understanding the merging behavior patterns at freeway on-ramps is important for assistanting the decisions of autonomous driving. This study develops a primitive-based framework to identify the driving patterns during merging processes and reveal th
e evolutionary mechanism at freeway on-ramps in congested traffic flow. The Nonhomogeneous Hidden Markov Model is introduced to decompose the merging processes into primitives containing semantic information. Then, the time-series K-means clustering is utilized to gather these primitives with variable-length time series into interpretable merging behavior patterns. Different from traditional state segmentation methods (e.g. Hidden Markov Model), the model proposed in this study considers the dependence of transition probability on exogenous variables, thereby revealing the influence of covariates on the evolution of driving patterns. This approach is evaluated in the merging area at a freeway on-ramp using the INTERACTION dataset. Results demonstrate that the approach provides an insight about the complicated merging processes. The findings about interpretable merging behavior patterns as well as the evolutionary mechanism can be used to design and improve the merging decision-making for autonomous vehicles.
Attention is a key mechanism for information selection in both biological brains and many state-of-the-art deep neural networks (DNNs). Here, we investigate whether humans and DNNs allocate attention in comparable ways when reading a text passage to
subsequently answer a specific question. We analyze 3 transformer-based DNNs that reach human-level performance when trained to perform the reading comprehension task. We find that the DNN attention distribution quantitatively resembles human attention distribution measured by fixation times. Human readers fixate longer on words that are more relevant to the question-answering task, demonstrating that attention is modulated by top-down reading goals, on top of lower-level visual and text features of the stimulus. Further analyses reveal that the attention weights in DNNs are also influenced by both top-down reading goals and lower-level stimulus features, with the shallow layers more strongly influenced by lower-level text features and the deep layers attending more to task-relevant words. Additionally, deep layers attention to task-relevant words gradually emerges when pre-trained DNN models are fine-tuned to perform the reading comprehension task, which coincides with the improvement in task performance. These results demonstrate that DNNs can evolve human-like attention distribution through task optimization, which suggests that human attention during goal-directed reading comprehension is a consequence of task optimization.
Pre-trained language models achieves high performance on machine reading comprehension (MRC) tasks but the results are hard to explain. An appealing approach to make models explainable is to provide rationales for its decision. To facilitate supervis
ed learning of human rationales, here we present PALRACE (Pruned And Labeled RACE), a new MRC dataset with human labeled rationales for 800 passages selected from the RACE dataset. We further classified the question to each passage into 6 types. Each passage was read by at least 26 participants, who labeled their rationales to answer the question. Besides, we conducted a rationale evaluation session in which participants were asked to answering the question solely based on labeled rationales, confirming that the labeled rationales were of high quality and can sufficiently support question answering.
Pre-trained language models have achieved human-level performance on many Machine Reading Comprehension (MRC) tasks, but it remains unclear whether these models truly understand language or answer questions by exploiting statistical biases in dataset
s. Here, we demonstrate a simple yet effective method to attack MRC models and reveal the statistical biases in these models. We apply the method to the RACE dataset, for which the answer to each MRC question is selected from 4 options. It is found that several pre-trained language models, including BERT, ALBERT, and RoBERTa, show consistent preference to some options, even when these options are irrelevant to the question. When interfered by these irrelevant options, the performance of MRC models can be reduced from human-level performance to the chance-level performance. Human readers, however, are not clearly affected by these irrelevant options. Finally, we propose an augmented training method that can greatly reduce models statistical biases.
In complex lane change (LC) scenarios, semantic interpretation and safety analysis of dynamic interactive pattern are necessary for autonomous vehicles to make appropriate decisions. This study proposes an unsupervised learning framework that combine
s primitive-based interactive pattern recognition methods and risk analysis methods. The Hidden Markov Model with the Gaussian mixture model (GMM-HMM) approach is developed to decompose the LC scenarios into primitives. Then the Dynamic Time Warping (DTW) distance based K-means clustering is applied to gather the primitives to 13 types of interactive patterns. Finally, this study considers two types of time-to-collision (TTC) involved in the LC process as indicators to analyze the risk of the interactive patterns and extract high-risk LC interactive patterns. The results obtained from The Highway Drone Dataset (highD) demonstrate that the identified LC interactive patterns contain interpretable semantic information. This study explores the spatiotemporal evolution law and risk formation mechanism of the LC interactive patterns and the findings are useful for comprehensively understanding the latent interactive patterns, improving the rationality and safety of autonomous vehicles decision-making.
Harnessing the quantum computation power of the present noisy-intermediate-size-quantum devices has received tremendous interest in the last few years. Here we study the learning power of a one-dimensional long-range randomly-coupled quantum spin cha
in, within the framework of reservoir computing. In time sequence learning tasks, we find the system in the quantum many-body localized (MBL) phase holds long-term memory, which can be attributed to the emergent local integrals of motion. On the other hand, MBL phase does not provide sufficient nonlinearity in learning highly-nonlinear time sequences, which we show in a parity check task. This is reversed in the quantum ergodic phase, which provides sufficient nonlinearity but compromises memory capacity. In a complex learning task of Mackey-Glass prediction that requires both sufficient memory capacity and nonlinearity, we find optimal learning performance near the MBL-to-ergodic transition. This leads to a guiding principle of quantum reservoir engineering at the edge of quantum ergodicity reaching optimal learning power for generic complex reservoir learning tasks. Our theoretical finding can be readily tested with present experiments.
Most conversational recommendation approaches are either not explainable, or they require external users knowledge for explaining or their explanations cannot be applied in real time due to computational limitations. In this work, we present a real t
ime category based conversational recommendation approach, which can provide concise explanations without prior user knowledge being required. We first perform an explainable user model in the form of preferences over the items categories, and then use the category preferences to recommend items. The user model is performed by applying a BERT-based neural architecture on the conversation. Then, we translate the user model into item recommendation scores using a Feed Forward Network. User preferences during the conversation in our approach are represented by category vectors which are directly interpretable. The experimental results on the real conversational recommendation dataset ReDial demonstrate comparable performance to the state-of-the-art, while our approach is explainable. We also show the potential power of our framework by involving an oracle setting of category preference prediction.
Lane-changing is an important driving behavior and unreasonable lane changes can result in potentially dangerous traffic collisions. Advanced Driver Assistance System (ADAS) can assist drivers to change lanes safely and efficiently. To capture the st
ochastic time series of lane-changing behavior, this study proposes a temporal convolutional network (TCN) to predict the long-term lane-changing trajectory and behavior. In addition, the convolutional neural network (CNN) and recurrent neural network (RNN) methods are considered as the benchmark models to demonstrate the learning ability of the TCN. The lane-changing dataset was collected by the driving simulator. The prediction performance of TCN is demonstrated from three aspects: different input variables, different input dimensions and different driving scenarios. Prediction results show that the TCN can accurately predict the long-term lane-changing trajectory and driving behavior with shorter computational time compared with two benchmark models. The TCN can provide accurate lane-changing prediction, which is one key information for the development of accurate ADAS.
We demonstrate experimentally the possibility of revealing fluctuations in the eigenfrequency of a resonator when the frequency noise is of the telegraph type. Using a resonantly driven micromechanical resonator, we show that the time-averaged vibrat
ion amplitude spectrum exhibits two peaks. They merge with an increasing rate of frequency switching and the spectrum displays an analog of motional narrowing. We also show that the moments of the complex amplitude depend strongly on the frequency noise characteristics. This dependence remains valid even when strong thermal or detector noise is present.
