Study analyzes IMDB movie comments and Twitter data using machine learning and vector space techniques.
problem Sentiment analysis of IMDB movie comments and Twitter data.
method Created a vector space in KNIME Analytics platform, used Decision Trees, Naïve Bayes, and SVM algorithms for classification.
result SVM algorithm provided the best classification results for both IMDB movie comments and Twitter data sets.
Proposes a new method for sentiment analysis using ensemble learning.
problem Capturing useful features for word-based sentiment analysis.
method Data Shared Adaptive Bootstrap Aggregated Lasso (AdaBag) Lasso.
result Demonstrates improved performance over PCA-LD in IMDb data.
Study shows pruning datasets can improve machine learning model performance.
problem Improving machine learning model performance through dataset pruning.
method Comparison of different algorithms on unpruned and iteratively pruned datasets.
result Algorithms that perform better on unpruned datasets also perform better on pruned datasets.
Combines BERT and graph CNN for improved text classification.
problem Text classification problems
method Combining BERT embedding and graph convolutional neural network
result Graph CNN model performs better than classical models combined with BERT
Improved Naive Bayes classifier with neural network models.
problem Limited complexity handling and independence assumption in Naive Bayes.
method Introducing Neural Naive Bayes and Neural Pooled Markov Chain models.
result Error rate reduced by 4.5 on IMDB dataset.
The paper evaluates three variants of the Gated Recurrent Unit (GRU) in recurrent neural networks (RNN) by reducing parameters in the update and reset gates. We evaluate the three variant GRU models on MNIST and IMDB datasets and show that these GRU-RNN variant models perform as well as the original GRU RNN model while…
Communities in social networks or graphs are sets of well-connected, overlapping vertices. The effectiveness of a community detection algorithm is determined by accuracy in finding the ground-truth communities and ability to scale with the size of the data. In this work, we provide three contributions. First, we show t…
The continually increasing number of complex datasets each year necessitates ever improving machine learning methods for robust and accurate categorization of these data. This paper introduces Random Multimodel Deep Learning (RMDL): a new ensemble, deep learning approach for classification. Deep learning models have ac…
Dropout and other feature noising schemes control overfitting by artificially corrupting the training data. For generalized linear models, dropout performs a form of adaptive regularization. Using this viewpoint, we show that the dropout regularizer is first-order equivalent to an L2 regularizer applied after scaling t…
Deep learning models detect and classify log anomalies.
problem Anomaly detection in unstructured log data.
method Auto-LSTM, Auto-BLSTM, and Auto-GRU models for feature extraction.
result Models outperform other algorithms on various log data sets.
This paper presents a novel model for multimodal learning based on gated neural networks. The Gated Multimodal Unit (GMU) model is intended to be used as an internal unit in a neural network architecture whose purpose is to find an intermediate representation based on a combination of data from different modalities. Th…
New method explains high-dimensional text classifiers.
problem Limited explainability tools for high-dimensional inputs and neural networks.
method Theoretical high-dimensional properties in neural networks.
result Improved explainability for neural network classifiers.
MOD improves ensemble-based uncertainty estimates by encouraging larger diversity.
problem Improving model uncertainty estimates for inputs not seen during training.
method Maximize Overall Diversity (MOD) approach to encourage larger diversity in ensemble predictions.
result Significantly improves predictive performance for out-of-distribution test examples.
Paper proposes a hybrid loss function for graph self-supervised learning.
problem Improving self-supervised representation learning for graphs.
method Hybrid loss function combining VICReg and HSIC.
result Hybrid loss function outperformed other methods in 4 out of 7 cases.
HTGCN improves community detection in dynamic, heterogeneous graphs.
problem Challenges in detecting communities in graphs with varying features and temporal dynamics.
method Designs HTGCN combining heterogeneous GCN and residual compressed aggregation for dynamic feature representation.
result HTGCN outperforms existing methods on DBLP and IMDB datasets.
New attacks bypass data sanitization defenses, increasing model errors.
problem Data poisoning attacks corrupt machine learning models trained on external data.
method Developed three attacks that coordinate poisoned points and formulate as optimization problems.
result 3% poisoned data increases test error from 3% to 24% on Enron spam detection.
New algorithm maintains privacy while improving model performance in selective release.
problem Privacy degradation and slow convergence in DPSGD.
method Differentially Private Selective Release based on Clipped Gradients (DPSR-CG).
result Maintains strict privacy guarantees while achieving exceptional model performance.
Simplified MDNs quantify uncertainty in large complex datasets.
problem Uncertainty quantification in large scale complex data.
method Simplified Mixture Density Networks (MDNs) for regression problems.
result Improved predictive log-likelihood and root-mean-square-error compared to existing methods.
RMDL combines multiple deep learning models for improved data classification.
problem Finding the best deep learning structure and architecture.
method Random Multimodel Deep Learning (RMDL) trains multiple DNN, CNN, and RNN models in parallel and combines their results.
result RMDL improves robustness and accuracy in data classification.
Approach generates adversarial text examples for robustness testing.
problem Measuring and improving the robustness of text classifiers.
method Reinforcement learning in a black-box setting.
result Successfully fools trained models with high success rates.
This paper proves a generalization bound for complex-valued neural networks scaling with spectral complexity.
problem Ensuring the performance of complex-valued neural networks on unseen data.
method Theoretical derivation using Maurey Sparsification Lemma and Dudley Entropy Integral, empirical validation on various datasets.
result The spectral complexity of weight matrices is a significant factor in the generalization ability of complex-valued neural networks.
Improved semi-supervised learning with advanced data augmentation.
problem Enhancing deep learning models with limited labeled data.
method Substitutes simple noising operations with advanced data augmentation methods like RandAugment and back-translation.
result Achieves substantial improvements across multiple tasks and datasets.
A new method selects models for ensemble learning to maximize mutual information, outperforming existing approaches.
problem Selecting models for ensemble learning to improve performance and reduce correlation issues.
method Formulate budgeted ensemble selection as maximizing mutual information, use Gaussian-copula to model correlated errors, propose a greedy mutual-information selection algorithm.
result Our method consistently outperforms strong baselines across multiple datasets.
Paper defends LSTM-based text classification models from backdoor attacks.
problem Backdoor attacks in LSTM models cause misclassification of spam or malicious speech.
method Backdoor Keyword Identification (BKI) to identify and exclude poisoned samples.
result BKI method effectively mitigates backdoor attacks in various text classification datasets.
We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and network architecture. They simply amount to at most a matrix inversion and mult…
Feature extraction has gained increasing attention in the field of machine learning, as in order to detect patterns, extract information, or predict future observations from big data, the urge of informative features is crucial. The process of extracting features is highly linked to dimensionality reduction as it impli…
Much work has been done in understanding human creativity and defining measures to evaluate creativity. This is necessary mainly for the reason of having an objective and automatic way of quantifying creative artifacts. In this work, we propose a regression-based learning framework which takes into account quantitative…
Novel BSG method for efficient stochastic optimization.
problem Efficient optimization of non-convex surfaces in stochastic settings.
method Binary search combined with first order gradient optimization.
result BSG produces more promising results and better generalization than other methods.
Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in natural sequential data such as speech. We unify successful ideas from recently pr…
We improve private training accuracy with learning rate schedules and matrix factorizations.
problem Private training with learning rate schedules and correlated noise.
method General upper and lower bounds for learning rate schedules, memory-efficient constructions, and schedule-aware factorizations.
result Schedule-aware factorizations improve accuracy in private training.
WTM reduces clause usage and computation time for pattern recognition.
problem High computation time and memory usage in Tsetlin Machine.
method Weighting clauses and using binomial sampling to reduce complexity.
result WTM achieves similar accuracy with fewer clauses and faster training.
In this paper, we combine ideas from machine learning (ML) and operations research and management science (OR/MS) in developing a framework, along with specific methods, for using data to prescribe optimal decisions in OR/MS problems. In a departure from other work on data-driven optimization and reflecting our practic…
SBMC method improves uncertainty estimation in deep learning models.
problem Improving uncertainty quantification in deep learning models.
method A scalable Bayesian Monte Carlo method using a model and parallel SMC/MCMC algorithm.
result SBMC achieves comparable or better accuracy and improved uncertainty quantification compared to state-of-the-art methods.
Attention mechanisms in deep learning become Gaussian process-like as the number of heads increases.
problem Understanding the behavior of attention mechanisms in deep learning models.
method Extending the equivalence between wide neural networks and Gaussian processes to attention architectures.
result Multi-head attention architectures behave as Gaussian processes as the number of heads tends to infinity.
Randomized Geometric Algebra for Convex Neural Networks Optimizes Transfer Learning.
problem Training neural networks to global optimality via convex optimization.
method Randomized algorithms in Clifford's Geometric Algebra for hypercomplex vector spaces.
result Convex optimization and geometric algebra improve LLMs' robustness and reliability in transfer learning.
This paper reformulates Fβ for better model performance and interpretation.
problem Optimizing model performance and interpretation using Fβ metric. method Reformulate Fβ metric to facilitate statistical distributions and dynamic penalty weights. result Better and interpretable results with a 14% boost in F1 score for IMDB data. Study compares BERT with other sentiment analysis models.
problem Comparing sentiment analysis techniques.
method Used four models: Sent WordNet, logistic regression, LSTM, and BERT on IMDB movie reviews.
result BERT outperformed other models in sentiment classification.
Most classifiers operate by selecting the maximum of an estimate of the conditional distribution p(y∣x) where x stands for the features of the instance to be classified and y denotes its label. This often results in a {\em hubristic bias}: overconfidence in the assignment of a definite label. Usually, the observa…
Faster Tsetlin Machines use clause indexing to speed inference and learning.
problem Overfitting and slow inference in Tsetlin Machines.
method Introduced a look-up table that indexes clauses based on feature falsification, enabling faster evaluation of clauses.
result Up to 15 times faster classification and three times faster learning on MNIST and Fashion-MNIST.
This study compares parallel SMC and MCMC for Bayesian deep learning, showing SMC parallel is faster.
problem Efficiently performing Bayesian deep learning with parallel computing.
method Compared sequential Monte Carlo (SMC) and Markov chain Monte Carlo (MCMC) in parallel settings.
result Parallel SMC achieves similar convergence as a single SMC but with reduced communication time.
Improved dataset distillation for images and texts boosts model accuracy.
problem Reducing dataset size for faster and more energy-efficient model training.
method Simultaneous distillation of images and soft labels, extending to text datasets.
result 2-4% increase in accuracy for image classification tasks, 20% reduction in distilled samples.
A new teacher-class network method compresses DNNs by distributing knowledge to multiple student networks.
problem Overwhelming size of Deep Neural Networks (DNNs).
method Single teacher with multiple student networks, transferring knowledge to each student.
result The combined knowledge of the class of students achieves better performance and reduces parameters.
SAFER method certifies robustness to word substitutions without model structure.
problem Certified robustness against synonymous word substitutions in NLP models.
method Randomized smoothing with stochastic ensemble of randomized inputs.
result Significantly outperforms state-of-the-art methods for certified robustness.
Transfer learning improves prediction quality in high-dimensional sparse regression.
problem Selecting hyperparameters for Lasso-based transfer learning algorithms.
method Asymptotic analysis using the replica method.
result Ignoring one type of transferred information has minimal impact on performance.
In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language model designed to directly capture the global semantic meaning relating words in a document via latent topics. Because of their sequential nature, RNNs are good at capturing the local structure of a word sequence - both semantic and syn…
New method improves interpretability of text adversarial examples.
problem Generating interpretable adversarial examples in text is challenging.
method Sparse Projected Gradient Descent (SPGD) with directional and sparsity constraints.
result Improves interpretability and likelihood of adversarial examples compared to state-of-the-art methods.
Attention layers are sensitive to single words, improving generalization over random features.
problem Understanding why attention layers are effective in NLP tasks.
method Study of word sensitivity in random features using BERT-Base word embeddings.
result Attention layers have high word sensitivity, improving generalization over random features.
The paper assesses text classification robustness through maximal safe radius computation.
problem Vulnerability of neural network models to small input modifications.
method Maximal safe radius computation, Monte Carlo Tree Search, syntactic filtering, linear bounding techniques.
result Approximation methods for computing upper and lower bounds of maximal safe radius.