Goto

Collaborating Authors

On Stacked Denoising Autoencoder based Pre-training of ANN for Isolated Handwritten Bengali Numerals Dataset Recognition

arXiv.org Machine Learning

This work attempts to find the most optimal parameter setting of a deep artificial neural network (ANN) for Bengali digit dataset by pre-training it using stacked denoising autoencoder (SDA). Although SDA based recognition is hugely popular in image, speech and language processing related tasks among the researchers, it was never tried in Bengali dataset recognition. For this work, a dataset of 70000 handwritten samples were used from (Chowdhury and Rahman, 2016) and was recognized using several settings of network architecture. Among all these settings, the most optimal setting being found to be five or more deeper hidden layers with sigmoid activation and one output layer with softmax activation. We proposed the optimal number of neurons that can be used in the hidden layer is 1500 or more. The minimum validation error found from this work is 2.34% which is the lowest error rate on handwritten Bengali dataset proposed till date.


An End-to-End Approach for Recognition of Modern and Historical Handwritten Numeral Strings

arXiv.org Machine Learning

An end-to-end solution for handwritten numeral string recognition is proposed, in which the numeral string is considered as composed of objects automatically detected and recognized by a YoLo-based model. The main contribution of this paper is to avoid heuristic-based methods for string preprocessing and segmentation, the need for task-oriented classifiers, and also the use of specific constraints related to the string length. A robust experimental protocol based on several numeral string datasets, including one composed of historical documents, has shown that the proposed method is a feasible end-to-end solution for numeral string recognition. Besides, it reduces the complexity of the string recognition task considerably since it drops out classical steps, in special preprocessing, segmentation, and a set of classifiers devoted to strings with a specific length.


Kannada-MNIST: A new handwritten digits dataset for the Kannada language

arXiv.org Machine Learning

In this paper, we disseminate a new handwritten digits-dataset, termed Kannada-MNIST, for the Kannada script, that can potentially serve as a direct drop-in replacement for the original MNIST dataset. In addition to this dataset, we disseminate an additional real world handwritten dataset (with $10k$ images), which we term as the Dig-MNIST dataset that can serve as an out-of-domain test dataset. We also duly open source all the code as well as the raw scanned images along with the scanner settings so that researchers who want to try out different signal processing pipelines can perform end-to-end comparisons. We provide high level morphological comparisons with the MNIST dataset and provide baselines accuracies for the dataset disseminated. The initial baselines obtained using an oft-used CNN architecture ($96.8\%$ for the main test-set and $76.1\%$ for the Dig-MNIST test-set) indicate that these datasets do provide a sterner challenge with regards to generalizability than MNIST or the KMNIST datasets. We also hope this dissemination will spur the creation of similar datasets for all the languages that use different symbols for the numeral digits.


Reinforcement Learning of Minimalist Numeral Grammars

arXiv.org Artificial Intelligence

Speech-controlled user interfaces facilitate the operation of devices and household functions to laymen. State-of-the-art language technology scans the acoustically analyzed speech signal for relevant keywords that are subsequently inserted into semantic slots to interpret the user's intent. In order to develop proper cognitive information and communication technologies, simple slot-filling should be replaced by utterance meaning transducers (UMT) that are based on semantic parsers and a \emph{mental lexicon}, comprising syntactic, phonetic and semantic features of the language under consideration. This lexicon must be acquired by a cognitive agent during interaction with its users. We outline a reinforcement learning algorithm for the acquisition of the syntactic morphology and arithmetic semantics of English numerals, based on minimalist grammar (MG), a recent computational implementation of generative linguistics. Number words are presented to the agent by a teacher in form of utterance meaning pairs (UMP) where the meanings are encoded as arithmetic terms from a suitable term algebra. Since MG encodes universal linguistic competence through inference rules, thereby separating innate linguistic knowledge from the contingently acquired lexicon, our approach unifies generative grammar and reinforcement learning, hence potentially resolving the still pending Chomsky-Skinner controversy.


Elon Musk and Grimes change baby's name: 'Roman numerals look better'

The Guardian

Tech entrepreneur Elon Musk and his partner Grimes have changed the unusual and largely unpronounceable name of their firstborn child. But anyone hoping that X Æ A-12 might be replaced by something a little more conventional, is going to be disappointed. In an Instagram post on Sunday, singer Grimes confirmed that the baby formerly known as X Æ A-12, would now be known as "X Æ A-Xii." Grimes gave no explanation for the change to using Roman Numerals, but later responded to a post asking if the alteration was made to comply with a California law that holds only the 26 letters of the alphabet can be used for child names. Looks better tbh," Grimes wrote. The couple appeared to have been at odds over how to interpret X Æ A-12 from the outset. The musician, whose real name is Claire Elise Boucher – previously explained that Æ is the Elven spelling of AI (for artificial intelligence) and explained "X" stands for "the unknown variable". Like how you said the letter A then I," wrote Grimes on Thursday in response to a query on Instagram.