Empirical Risk Minimization (ERM) based machine learning algorithms have suffered from weak generalization performance on data obtained from out-of-distribution (OOD). To address this problem, Invariant Risk Minimization (IRM) objective was suggested to find invariant optimal predictor which is less affected by the changes in data distribution. However, even with such progress, IRMv1, the practical formulation of IRM, still shows performance degradation when there are not enough training data, and even fails to generalize to OOD, if the number of spurious correlations is larger than the number of environments. In this paper, to address such problems, we propose a novel meta-learning based approach for IRM. In this method, we do not assume the linearity of classifier for the ease of optimization, and solve ideal bi-level IRM objective with Model-Agnostic Meta-Learning (MAML) framework. Our method is more robust to the data with spurious correlations and can provide an invariant optimal classifier even when data from each distribution are scarce. In experiments, we demonstrate that our algorithm not only has better OOD generalization performance than IRMv1 and all IRM variants, but also addresses the weakness of IRMv1 with improved stability.
A differentiable neural computer (DNC) is a memory augmented neural network devised to solve a wide range of algorithmic and question answering tasks and it showed promising performance in a variety of domains. However, its single memory-based operations are not enough to store and retrieve diverse informative representations existing in many tasks. Furthermore, DNC does not explicitly consider the memorization itself as a target objective, which inevitably leads to a very slow learning speed of the model. To address those issues, we propose a novel distributed memory-based self-supervised DNC architecture for enhanced memory augmented neural network performance. We introduce (i) a multiple distributed memory block mechanism that stores information independently to each memory block and uses stored information in a cooperative way for diverse representation and (ii) a self-supervised memory loss term which ensures how well a given input is written to the memory. Our experiments on algorithmic and question answering tasks show that the proposed model outperforms all other variations of DNC in a large margin, and also matches the performance of other state-of-the-art memory-based network models.
Generating music with emotion similar to that of an input video is a very relevant issue nowadays. Video content creators and automatic movie directors benefit from maintaining their viewers engaged, which can be facilitated by producing novel material eliciting stronger emotions in them. Moreover, there's currently a demand for more empathetic computers to aid humans in applications such as augmenting the perception ability of visually and/or hearing impaired people. Current approaches overlook the video's emotional characteristics in the music generation step, only consider static images instead of videos, are unable to generate novel music, and require a high level of human effort and skills. In this study, we propose a novel hybrid deep neural network that uses an Adaptive Neuro-Fuzzy Inference System to predict a video's emotion from its visual features and a deep Long Short-Term Memory Recurrent Neural Network to generate its corresponding audio signals with similar emotional inkling. The former is able to appropriately model emotions due to its fuzzy properties, and the latter is able to model data with dynamic time properties well due to the availability of the previous hidden state information. The novelty of our proposed method lies in the extraction of visual emotional features in order to transform them into audio signals with corresponding emotional aspects for users. Quantitative experiments show low mean absolute errors of 0.217 and 0.255 in the Lindsey and DEAP datasets respectively, and similar global features in the spectrograms. This indicates that our model is able to appropriately perform domain transformation between visual and audio features. Based on experimental results, our model can effectively generate audio that matches the scene eliciting a similar emotion from the viewer in both datasets, and music generated by our model is also chosen more often.
Mel-frequency filter bank (MFB) based approaches have the advantage of learning speech compared to raw spectrum since MFB has less feature size. However, speech generator with MFB approaches require additional vocoder that needs a huge amount of computation expense for training process. The additional pre/post processing such as MFB and vocoder is not essential to convert real human speech to others. It is possible to only use the raw spectrum along with the phase to generate different style of voices with clear pronunciation. In this regard, we propose a fast and effective approach to convert realistic voices using raw spectrum in a parallel manner. Our transformer-based model architecture which does not have any CNN or RNN layers has shown the advantage of learning fast and solved the limitation of sequential computation of conventional RNN. In this paper, we introduce a vocoder-free end-to-end voice conversion method using transformer network. The presented conversion model can also be used in speaker adaptation for speech recognition. Our approach can convert the source voice to a target voice without using MFB and vocoder. We can get an adapted MFB for speech recognition by multiplying the converted magnitude with phase. We perform our voice conversion experiments on TIDIGITS dataset using the metrics such as naturalness, similarity, and clarity with mean opinion score, respectively.
In this paper, we propose Stacked DeBERT, short for Stacked Denoising Bidirectional Encoder Representations from Transformers. This novel model improves robustness in incomplete data, when compared to existing systems, by designing a novel encoding scheme in BERT, a powerful language representation model solely based on attention mechanisms. Incomplete data in natural language processing refer to text with missing or incorrect words, and its presence can hinder the performance of current models that were not implemented to withstand such noises, but must still perform well even under duress. This is due to the fact that current approaches are built for and trained with clean and complete data, and thus are not able to extract features that can adequately represent incomplete data. Our proposed approach consists of obtaining intermediate input representations by applying an embedding layer to the input tokens followed by vanilla transformers. These intermediate features are given as input to novel denoising transformers which are responsible for obtaining richer input representations. The proposed approach takes advantage of stacks of multilayer perceptrons for the reconstruction of missing words' embeddings by extracting more abstract and meaningful hidden feature vectors, and bidirectional transformers for improved embedding representation. We consider two datasets for training and evaluation: the Chatbot Natural Language Understanding Evaluation Corpus and Kaggle's Twitter Sentiment Corpus. Our model shows improved F1-scores and better robustness in informal/incorrect texts present in tweets and in texts with Speech-to-Text error in the sentiment and intent classification tasks.
Conventional solar cells are predominately designed similar to a stacked structure. Optimizing the layer thicknesses in this stack structure is crucial to extract the best efficiency of the solar cell. The commonplace method used in optimization simulations, such as for optimizing the optical spacer layers' thicknesses, is the parameter sweep. Our experiments show that the introduction of genetic algorithm based method results in a significantly faster and accurate search method when compared to brute-force parameter sweep method in both single and multi-layer optimization. While other sweep methods can also outperform the brute-force method, they do not consistently exhibit $100\%$ accuracy in the optimized results like our genetic algorithm. Our best case scenario was observed to utilize 57.9% less simulations than brute-force method.
We propose to use Genetic Algorithm (GA), inspired by Darwin's evolution theory, to optimize the search for the optimal thickness in organic solar cell's layers with regards to maximizing the short-circuit current density. The conventional method used in optimization simulations, such as for optimizing the optical spacer layers' thicknesses, is the parameter sweep. Our experiments show that the introduction of GA results in a significantly faster and accurate search method when compared to brute-force parameter sweep method in both single and multi-layer optimization.
Inspired by the recent advances in generative models, we introduce a human action generation model in order to generate a consecutive sequence of human motions to formulate novel actions. We propose a framework of an autoencoder and a generative adversarial network (GAN) to produce multiple and consecutive human actions conditioned on the initial state and the given class label. The proposed model is trained in an end-to-end fashion, where the autoencoder is jointly trained with the GAN. The model is trained on the NTU RGB+D dataset and we show that the proposed model can generate different styles of actions. Moreover, the model can successfully generate a sequence of novel actions given different action labels as conditions. The conventional human action prediction and generation models lack those features, which are essential for practical applications.
We show Correspondence Analysis (CA) is equivalent to defining Gini-index with appropriate scaled one-hot encoding. Using this relation, we introduce non-linear kernel extension of CA. The extended CA gives well-known analysis for categorical data (CD) and natural language processing by specializing kernels. For example, our formulation can give G-test, skip-gram with negative-sampling (SGNS), and GloVe as a special case. We introduce two kernels for natural language processing based on our formulation. First is a stop word(SW) kernel. Second is word similarity(WS) kernel. The SW kernel is the system introducing appropriate weights for SW. The WS kernel enables to use WS test data as training data for vector space representations of words. We show these kernels enhances accuracy when training data is not sufficiently large.
In this work, we introduce temporal hierarchies to the sequence to sequence (seq2seq) model to tackle the problem of abstractive summarization of scientific articles. The proposed Multiple Timescale model of the Gated Recurrent Unit (MTGRU) is implemented in the encoder-decoder setting to better deal with the presence of multiple compositionalities in larger texts. The proposed model is compared to the conventional RNN encoder-decoder, and the results demonstrate that our model trains faster and shows significant performance gains. The results also show that the temporal hierarchies help improve the ability of seq2seq models to capture compositionalities better without the presence of highly complex architectural hierarchies.