A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New image classifier uses hierarchical max-pooling with local pooling.
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothin…
Sound event detection (SED) methods are tasked with labeling segments of audio recordings by the presence of active sound sources. SED is typically posed as a supervised machine learning problem, requiring strong annotations for the presence or absence of each sound source at every time instant within the recording. Ho…
Max-pooling architectures are theoretically analyzed and shown to be globally optimized and generalize well.
Convolutional neural networks (CNNs) have achieved remarkable performance in many applications, especially in image recognition tasks. As a crucial component of CNNs, sub-sampling plays an important role for efficient training or invariance property, and max-pooling and arithmetic average-pooling are commonly used sub-…
The paper addresses instability in CNNs' first layer by proving max pooling's shift invariance.
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convoluti…
New approach reduces malware detection memory requirements and speeds up training.
We seek to improve deep neural networks by generalizing the pooling operations that play a central role in current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in (1) learning a pooling function via (…
New CNN initialization scheme derived from modern architectures.
Paper introduces a conformer-based system for streaming language identification in long-form speech.
Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of …
We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states. We propose a model inspired by the recent success of dilated convolutions in sequence modeling applications, allowin…
Deep network solves maze path planning without training.
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Based on the recent DeepSets architecture proposed by Zaheer et al. (NIPS 2017), we introduce a Set Aggregation Network (SAN) as an alternative…
This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer. Max-pooling layer discards the pose, i.e., translational and rotational relationship betwe…
Acoustic scenes are rich and redundant in their content. In this work, we present a spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network to learn from patterns that are discriminative while suppressing those that are irrelevant for acoustic scene classification. The convolutiona…
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling…
Deep neural networks have become commonplace in the domain of reinforcement learning, but are often expensive in terms of the number of parameters needed. While compressing deep neural networks has of late assumed great importance to overcome this drawback, little work has been done to address this problem in the conte…
We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories compri…
Improved TD learning with neural nets reduces sample complexity and overparameterization.
The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is crucial, e.g. traffic networks and financial transaction graphs. Despite the constant progress made on learning structured data, there is s…
Discrete Fourier transforms provide a significant speedup in the computation of convolutions in deep learning. In this work, we demonstrate that, beyond its advantages for efficient computation, the spectral domain also provides a powerful representation in which to model and train convolutional neural networks (CNNs).…
Optimal rebalancing strategy improves AMM pool performance by 25%.
Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to stronger visual differences due to different identities. State-of-the-art methods normally use complex deep learning models such as recurren…
Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolutional networks (convnets), incorporating rectifier units and max-pooling, are neither smooth nor convex. Standard guarantees therefore do n…
New protocol evaluates synthetic data for temporal consistency.
EarnMore uses masked stock representations to train RL agents for customizable stock pools efficiently.
Proposes SimPool for graph pooling using structural similarity features.
Nonlinearity is crucial to the performance of a deep (neural) network (DN). To date there has been little progress understanding the menagerie of available nonlinearities, but recently progress has been made on understanding the rôle played by piecewise affine and convex nonlinearities like the ReLU and absolute value …
Debona improves neural network verification by faster and tighter bounds.
Generalization error defines the discriminability and the representation power of a deep model. In this work, we claim that feature space design using deep compositional function plays a significant role in generalization along with explicit and implicit regularizations. Our claims are being established with several im…
Long short-term memory (LSTM) is normally used in recurrent neural network (RNN) as basic recurrent unit. However,conventional LSTM assumes that the state at current time step depends on previous time step. This assumption constraints the time dependency modeling capability. In this study, we propose a new variation of…
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. …
TD learning reduces prediction error in Markov chain problems.
Develops methods to answer counterfactual questions in temporal point processes.
Novel hybrid bilinear model improves epilepsy diagnosis accuracy.
Broker uses multi-task dynamic pricing to learn competitive prices in credit markets.
Capitalizing on the need for addressing the existing challenges associated with gesture recognition via sparse multichannel surface Electromyography (sEMG) signals, the paper proposes a novel deep learning model, referred to as the XceptionTime architecture. The proposed innovative XceptionTime is designed by integrati…
Convolutional neural networks learn effective summary statistics for ABC inference.
We propose a new way of thinking about deep neural networks, in which the linear and non-linear components of the network are naturally derived and justified in terms of principles in probability theory. In particular, the models constructed in our framework assign probabilities to uncertain realizations, leading to Ku…
Paper improves generalization bounds for multi-kernel learning with mixed datasets.
Proposes log density gradient to improve reinforcement learning sample complexity.
ExNODE uses ODE to model sets with permutation equivariance.
Dynamic-weight AMMs outperform traditional CEX rebalancing in tokenized funds, especially on L2s.
Paper proposes NNAFC for automatic financial factor construction.
Capsule network (CapsNet) was introduced as an enhancement over convolutional neural networks, supplementing the latter's invariance properties with equivariance through pose estimation. CapsNet achieved a very decent performance with a shallow architecture and a significant reduction in parameters count. However, the …
Syndrome differentiation in Traditional Chinese Medicine (TCM) is the process of understanding and reasoning body condition, which is the essential step and premise of effective treatments. However, due to its complexity and lack of standardization, it is challenging to achieve. In this study, we consider each patient'…