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.
High-performance neural network training on a cluster of Pentium III processors.
Transfer learning does not improve character recognition performance.
It is proposed a new code for contours of plane images. This code was applied for optical character recognition of printed and handwritten characters. One can apply it to recognition of any visual images.
Bayesian method improves neural net convergence for character recognition.
Labels distilled from images improve model training efficiency and flexibility.
Non-autoregressive transformer improves speech recognition speed and accuracy.
End-to-end speech synthesis is a promising approach that directly converts raw text to speech. Although it was shown that Tacotron2 outperforms classical pipeline systems with regards to naturalness in English, its applicability to other languages is still unknown. Japanese could be one of the most difficult languages …
This abstract explores an RNN-based approach to online handwritten recognition problem. Our method uses data from an accelerometer and a gyroscope mounted on a handheld pen-like device to train and run a character pre-diction model. We have built a dataset of timestamped gyroscope and accelerometer data gathered during…
Amharic is the official language of the Federal Democratic Republic of Ethiopia. There are lots of historic Amharic and Ethiopic handwritten documents addressing various relevant issues including governance, science, religious, social rules, cultures and art works which are very reach indigenous knowledge. The Amharic …
End-to-end automatic speech recognition (ASR) commonly transcribes audio signals into sequences of characters while its performance is evaluated by measuring the word-error rate (WER). This suggests that predicting sequences of words directly may be helpful instead. However, training with word-level supervision can be …
Convolution Neural Networks (CNN) have recently achieved state-of-the art performance on handwritten Chinese character recognition (HCCR). However, most of CNN models employ the SoftMax activation function and minimize cross entropy loss, which may cause loss of inter-class information. To cope with this problem, we pr…
EASTER improves OCR efficiency and scalability.
Gaussian Process upsampling boosts OCR accuracy from low-res images.
Random forests classify Pokemon names based on evolutionary status.
Many studies have been undertaken by using machine learning techniques, including neural networks, to predict stock returns. Recently, a method known as deep learning, which achieves high performance mainly in image recognition and speech recognition, has attracted attention in the machine learning field. This paper im…
Paper proposes a framework to protect user anonymity in emotion recognition.
Investigates neural TTS systems for Japanese and English.
Study builds a Japanese financial-specific LLM through continual pre-training.
The paper approaches the task of handwritten text recognition (HTR) with attentional encoder-decoder networks trained on sequences of characters, rather than words. We experiment on lines of text from popular handwriting datasets and compare different activation functions for the attention mechanism used for aligning i…
ChemGrapher uses deep learning to automatically convert chemical compound images into accurate graphs.
This paper presents a recognition system for handwritten Pashto letters. However, handwritten character recognition is a challenging task. These letters not only differ in shape and style but also vary among individuals. The recognition becomes further daunting due to the lack of standard datasets for inscribed Pashto …
A tailored HTR system improves CER to 0.015 for medieval Latin.
Study shows activist board representation improves Japanese companies' performance.
KaoKore dataset extracts faces from pre-modern Japanese art for machine learning.
Deep learning detects bid-rigging cartels with high accuracy.
This paper presents a novel kernel-based generative classifier which is defined in a distortion subspace using polynomial series expansion, named Kernel-Distortion (KD) classifier. An iterative kernel selection algorithm is developed to steadily improve classification performance by repeatedly removing and adding kerne…
Study constructs a Japanese financial LLM benchmark.
Study finds varying market efficiency in prewar and wartime Japanese stock market.
Study on time-varying APT validity in Japanese stock market.
We develop a Chern character map for twisted equivariant non-abelian cohomology.
AV-ASR system improves speech recognition with visual context.
This study evaluates prewar Japanese financial market efficiency using time-varying models.
Scene text magnifier aims to magnify text in natural scene images without recognition. It could help the special groups, who have myopia or dyslexia to better understand the scene. In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, char…
Classification of sequence data is the topic of interest for dynamic Bayesian models and Recurrent Neural Networks (RNNs). While the former can explicitly model the temporal dependencies between class variables, the latter have a capability of learning representations. Several attempts have been made to improve perform…
HW2MP-GAN tackles ancient handwritten text recognition.
Network analysis techniques remain rarely used for understanding international management strategies. Our paper highlights their value as research tool in this field of social science using a large set of micro-data (20,000) to investigate the presence of networks of subsidiaries overseas. The research question is the …
Paper proposes a method to maintain ASR performance on new tasks without forgetting old ones.
We investigated the network structures of the Japanese stock market through the minimum spanning tree. We defined grouping coefficient to test the validity of conventional grouping by industrial categories, and found a decreasing in trend for the coefficient. This phenomenon supports the increasing external influences …
Paper proposes an online speech recognition model using Transformer.
In this paper, we propose and develop the novel idea of treating musical sheets as literary documents in the traditional text analytics parlance, to fully benefit from the vast amount of research already existing in statistical text mining and topic modelling. We specifically introduce the idea of representing any give…
Study examines asymmetry impacts on Japanese stock market volatility modeling and forecasting.
The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In this contribution, we analyse an attention-based seq2seq speech recognition syste…
We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regularizer for RNNs including LSTMs and IRNNs, improving performance on character-level language modeling and phoneme recognition, and outperfor…
Improved recurrent neural networks learn long-term dependencies through multi-scale memory.
FGN improves Chinese NER by integrating glyph information and interactive context.
In this paper, we address the task of Optical Character Recognition(OCR) for the Telugu script. We present an end-to-end framework that segments the text image, classifies the characters and extracts lines using a language model. The segmentation is based on mathematical morphology. The classification module, which is …
Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been call…
This paper examines the integration process of the Japanese major rice markets (Tokyo and Osaka) from 1881 to 1932. Using a non-Bayesian time-varying vector error correction model, we argue that the process strongly depended on the government's policy on the network system of the telegram and telephone; rice traders wi…