Paper Group ANR 571
Combinets: Creativity via Recombination of Neural Networks. MOEA/D with Angle-based Constrained Dominance Principle for Constrained Multi-objective Optimization Problems. Incremental Training of Deep Convolutional Neural Networks. Removing out-of-focus blur from a single image. Intrinsic Geometric Vulnerability of High-Dimensional Artificial Intell …
Combinets: Creativity via Recombination of Neural Networks
| Title | Combinets: Creativity via Recombination of Neural Networks |
| Authors | Matthew Guzdial, Mark O. Riedl |
| Abstract | One of the defining characteristics of human creativity is the ability to make conceptual leaps, creating something surprising from typical knowledge. In comparison, deep neural networks often struggle to handle cases outside of their training data, which is especially problematic for problems with limited training data. Approaches exist to transfer knowledge from problems with sufficient data to those with insufficient data, but they tend to require additional training or a domain-specific method of transfer. We present a new approach, conceptual expansion, that serves as a general representation for reusing existing trained models to derive new models without backpropagation. We evaluate our approach on few-shot variations of two tasks: image classification and image generation, and outperform standard transfer learning approaches. |
| Tasks | Image Classification, Image Generation, Transfer Learning |
| Published | 2018-02-10 |
| URL | http://arxiv.org/abs/1802.03605v4 |
| http://arxiv.org/pdf/1802.03605v4.pdf | |
| PWC | https://paperswithcode.com/paper/combinets-creativity-via-recombination-of |
| Repo | |
| Framework | |
MOEA/D with Angle-based Constrained Dominance Principle for Constrained Multi-objective Optimization Problems
| Title | MOEA/D with Angle-based Constrained Dominance Principle for Constrained Multi-objective Optimization Problems |
| Authors | Zhun Fan, Yi Fang, Wenji Li, Xinye Cai, Caimin Wei, Erik Goodman |
| Abstract | This paper proposes a novel constraint-handling mechanism named angle-based constrained dominance principle (ACDP) embedded in a decomposition-based multi-objective evolutionary algorithm (MOEA/D) to solve constrained multi-objective optimization problems (CMOPs). To maintain the diversity of the working population, ACDP utilizes the information of the angle of solutions to adjust the dominance relation of solutions during the evolutionary process. This paper uses 14 benchmark instances to evaluate the performance of the MOEA/D with ACDP (MOEA/D-ACDP). Additionally, an engineering optimization problem (which is I-beam optimization problem) is optimized. The proposed MOEA/D-ACDP, and four other decomposition-based CMOEAs, including C-MOEA/D, MOEA/D-CDP, MOEA/D-Epsilon and MOEA/D-SR are tested by the above benchmarks and the engineering application. The experimental results manifest that MOEA/D-ACDP is significantly better than the other four CMOEAs on these test instances and the real-world case, which indicates that ACDP is more effective for solving CMOPs. |
| Tasks | |
| Published | 2018-02-10 |
| URL | http://arxiv.org/abs/1802.03608v1 |
| http://arxiv.org/pdf/1802.03608v1.pdf | |
| PWC | https://paperswithcode.com/paper/moead-with-angle-based-constrained-dominance |
| Repo | |
| Framework | |
Incremental Training of Deep Convolutional Neural Networks
| Title | Incremental Training of Deep Convolutional Neural Networks |
| Authors | Roxana Istrate, Adelmo Cristiano Innocenza Malossi, Costas Bekas, Dimitrios Nikolopoulos |
| Abstract | We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network, we introduce a look-ahead initialization that outperforms the random initialization. We demonstrate that our incremental approach reaches the reference network baseline accuracy. Additionally, it allows to identify smaller partitions of the original state-of-the-art network, that deliver the same final accuracy, by using only a fraction of the global number of parameters. This allows for a potential speedup of the training time of several factors. We report training results on CIFAR-10 for ResNet and VGGNet. |
| Tasks | |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.10232v1 |
| http://arxiv.org/pdf/1803.10232v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-training-of-deep-convolutional |
| Repo | |
| Framework | |
Removing out-of-focus blur from a single image
| Title | Removing out-of-focus blur from a single image |
| Authors | Guodong Xu, Chaoqiang Liu, Hui Ji |
| Abstract | Reproducing an all-in-focus image from an image with defocus regions is of practical value in many applications, eg, digital photography, and robotics. Using the output of some existing defocus map estimator, existing approaches first segment a de-focused image into multiple regions blurred by Gaussian kernels with different variance each, and then de-blur each region using the corresponding Gaussian kernel. In this paper, we proposed a blind deconvolution method specifically designed for removing defocus blurring from an image, by providing effective solutions to two critical problems: 1) suppressing the artifacts caused by segmentation error by introducing an additional variable regularized by weighted $\ell_0$-norm; and 2) more accurate defocus kernel estimation using non-parametric symmetry and low-rank based constraints on the kernel. The experiments on real datasets showed the advantages of the proposed method over existing ones, thanks to the effective treatments of the two important issues mentioned above during deconvolution. |
| Tasks | |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09166v1 |
| http://arxiv.org/pdf/1808.09166v1.pdf | |
| PWC | https://paperswithcode.com/paper/removing-out-of-focus-blur-from-a-single |
| Repo | |
| Framework | |
Intrinsic Geometric Vulnerability of High-Dimensional Artificial Intelligence
| Title | Intrinsic Geometric Vulnerability of High-Dimensional Artificial Intelligence |
| Authors | Luca Bortolussi, Guido Sanguinetti |
| Abstract | The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets. Despite recent high-profile successes, empirical evidence indicates that the high predictive performance is often paired with low robustness, making AI systems potentially vulnerable to adversarial attacks. In this report, we provide a simple intuitive argument suggesting that high performance and vulnerability are intrinsically coupled, and largely dependent on the geometry of typical, high-dimensional data sets. Our work highlights a major potential pitfall of modern AI systems, and suggests practical research directions to ameliorate the problem. |
| Tasks | |
| Published | 2018-11-08 |
| URL | http://arxiv.org/abs/1811.03571v2 |
| http://arxiv.org/pdf/1811.03571v2.pdf | |
| PWC | https://paperswithcode.com/paper/intrinsic-geometric-vulnerability-of-high |
| Repo | |
| Framework | |
Learning through deterministic assignment of hidden parameters
| Title | Learning through deterministic assignment of hidden parameters |
| Authors | Jian Fang, Shaobo Lin, Zongben Xu |
| Abstract | Supervised learning frequently boils down to determining hidden and bright parameters in a parameterized hypothesis space based on finite input-output samples. The hidden parameters determine the attributions of hidden predictors or the nonlinear mechanism of an estimator, while the bright parameters characterize how hidden predictors are linearly combined or the linear mechanism. In traditional learning paradigm, hidden and bright parameters are not distinguished and trained simultaneously in one learning process. Such an one-stage learning (OSL) brings a benefit of theoretical analysis but suffers from the high computational burden. To overcome this difficulty, a two-stage learning (TSL) scheme, featured by learning through deterministic assignment of hidden parameters (LtDaHP) was proposed, which suggests to deterministically generate the hidden parameters by using minimal Riesz energy points on a sphere and equally spaced points in an interval. We theoretically show that with such deterministic assignment of hidden parameters, LtDaHP with a neural network realization almost shares the same generalization performance with that of OSL. We also present a series of simulations and application examples to support the outperformance of LtDaHP |
| Tasks | |
| Published | 2018-03-22 |
| URL | http://arxiv.org/abs/1803.08374v2 |
| http://arxiv.org/pdf/1803.08374v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-through-deterministic-assignment-of |
| Repo | |
| Framework | |
Shaping Influence and Influencing Shaping: A Computational Red Teaming Trust-based Swarm Intelligence Model
| Title | Shaping Influence and Influencing Shaping: A Computational Red Teaming Trust-based Swarm Intelligence Model |
| Authors | Jiangjun Tang, Eleni Petraki, Hussein Abbass |
| Abstract | Sociotechnical systems are complex systems, where nonlinear interaction among different players can obscure causal relationships. The absence of mechanisms to help us understand how to create a change in the system makes it hard to manage these systems. Influencing and shaping are social operators acting on sociotechnical systems to design a change. However, the two operators are usually discussed in an ad-hoc manner, without proper guiding models and metrics which assist in adopting these models successfully. Moreover, both social operators rely on accurate understanding of the concept of trust. Without such understanding, neither of these operators can create the required level to create a change in a desirable direction. In this paper, we define these concepts in a concise manner suitable for modelling the concepts and understanding their dynamics. We then introduce a model for influencing and shaping and use Computational Red Teaming principles to design and demonstrate how this model operates. We validate the results computationally through a simulation environment to show social influencing and shaping in an artificial society. |
| Tasks | |
| Published | 2018-02-26 |
| URL | http://arxiv.org/abs/1802.09647v1 |
| http://arxiv.org/pdf/1802.09647v1.pdf | |
| PWC | https://paperswithcode.com/paper/shaping-influence-and-influencing-shaping-a |
| Repo | |
| Framework | |
Dreaming neural networks: forgetting spurious memories and reinforcing pure ones
| Title | Dreaming neural networks: forgetting spurious memories and reinforcing pure ones |
| Authors | Alberto Fachechi, Elena Agliari, Adriano Barra |
| Abstract | The standard Hopfield model for associative neural networks accounts for biological Hebbian learning and acts as the harmonic oscillator for pattern recognition, however its maximal storage capacity is $\alpha \sim 0.14$, far from the theoretical bound for symmetric networks, i.e. $\alpha =1$. Inspired by sleeping and dreaming mechanisms in mammal brains, we propose an extension of this model displaying the standard on-line (awake) learning mechanism (that allows the storage of external information in terms of patterns) and an off-line (sleep) unlearning$&$consolidating mechanism (that allows spurious-pattern removal and pure-pattern reinforcement): this obtained daily prescription is able to saturate the theoretical bound $\alpha=1$, remaining also extremely robust against thermal noise. Both neural and synaptic features are analyzed both analytically and numerically. In particular, beyond obtaining a phase diagram for neural dynamics, we focus on synaptic plasticity and we give explicit prescriptions on the temporal evolution of the synaptic matrix. We analytically prove that our algorithm makes the Hebbian kernel converge with high probability to the projection matrix built over the pure stored patterns. Furthermore, we obtain a sharp and explicit estimate for the “sleep rate” in order to ensure such a convergence. Finally, we run extensive numerical simulations (mainly Monte Carlo sampling) to check the approximations underlying the analytical investigations (e.g., we developed the whole theory at the so called replica-symmetric level, as standard in the Amit-Gutfreund-Sompolinsky reference framework) and possible finite-size effects, finding overall full agreement with the theory. |
| Tasks | |
| Published | 2018-10-29 |
| URL | http://arxiv.org/abs/1810.12217v1 |
| http://arxiv.org/pdf/1810.12217v1.pdf | |
| PWC | https://paperswithcode.com/paper/dreaming-neural-networks-forgetting-spurious |
| Repo | |
| Framework | |
Evaluating Patient Readmission Risk: A Predictive Analytics Approach
| Title | Evaluating Patient Readmission Risk: A Predictive Analytics Approach |
| Authors | Avishek Choudhury, Christopher M Greene |
| Abstract | With the emergence of the Hospital Readmission Reduction Program of the Center for Medicare and Medicaid Services on October 1, 2012, forecasting unplanned patient readmission risk became crucial to the healthcare domain. There are tangible works in the literature emphasizing on developing readmission risk prediction models; However, the models are not accurate enough to be deployed in an actual clinical setting. Our study considers patient readmission risk as the objective for optimization and develops a useful risk prediction model to address unplanned readmissions. Furthermore, Genetic Algorithm and Greedy Ensemble is used to optimize the developed model constraints. |
| Tasks | |
| Published | 2018-12-11 |
| URL | https://arxiv.org/abs/1812.11028v2 |
| https://arxiv.org/pdf/1812.11028v2.pdf | |
| PWC | https://paperswithcode.com/paper/181211028 |
| Repo | |
| Framework | |
Coupled Analysis Dictionary Learning to inductively learn inversion: Application to real-time reconstruction of Biomedical signals
| Title | Coupled Analysis Dictionary Learning to inductively learn inversion: Application to real-time reconstruction of Biomedical signals |
| Authors | Kavya Gupta, Brojeshwar Bhowmick, Angshul Majumdar |
| Abstract | This work addresses the problem of reconstructing biomedical signals from their lower dimensional projections. Traditionally Compressed Sensing (CS) based techniques have been employed for this task. These are transductive inversion processes, the problem with these approaches is that the inversion is time-consuming and hence not suitable for real-time applications. With the recent advent of deep learning, Stacked Sparse Denoising Autoencoder (SSDAE) has been used for learning inversion in an inductive setup. The training period for inductive learning is large but is very fast during application – capable of real-time speed. This work proposes a new approach for inductive learning of the inversion process. It is based on Coupled Analysis Dictionary Learning. Results on Biomedical signal reconstruction show that our proposed approach is very fast and yields result far better than CS and SSDAE. |
| Tasks | Denoising, Dictionary Learning |
| Published | 2018-12-24 |
| URL | http://arxiv.org/abs/1812.09878v1 |
| http://arxiv.org/pdf/1812.09878v1.pdf | |
| PWC | https://paperswithcode.com/paper/coupled-analysis-dictionary-learning-to |
| Repo | |
| Framework | |
Approximate Model Counting by Partial Knowledge Compilation
| Title | Approximate Model Counting by Partial Knowledge Compilation |
| Authors | Yong Lai |
| Abstract | Model counting is the problem of computing the number of satisfying assignments of a given propositional formula. Although exact model counters can be naturally furnished by most of the knowledge compilation (KC) methods, in practice, they fail to generate the compiled results for the exact counting of models for certain formulas due to the explosion in sizes. Decision-DNNF is an important KC language that captures most of the practical compilers. We propose a generalized Decision-DNNF (referred to as partial Decision-DNNF) via introducing a class of new leaf vertices (called unknown vertices), and then propose an algorithm called PartialKC to generate randomly partial Decision-DNNF formulas from the given formulas. An unbiased estimate of the model number can be computed via a randomly partial Decision-DNNF formula. Each calling of PartialKC consists of multiple callings of MicroKC, while each of the latter callings is a process of importance sampling equipped with KC technologies. The experimental results show that PartialKC is more accurate than both SampleSearch and SearchTreeSampler, PartialKC scales better than SearchTreeSampler, and the KC technologies can obviously accelerate sampling. |
| Tasks | |
| Published | 2018-05-18 |
| URL | http://arxiv.org/abs/1805.07180v1 |
| http://arxiv.org/pdf/1805.07180v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-model-counting-by-partial |
| Repo | |
| Framework | |
Towards Coherent and Cohesive Long-form Text Generation
| Title | Towards Coherent and Cohesive Long-form Text Generation |
| Authors | Woon Sang Cho, Pengchuan Zhang, Yizhe Zhang, Xiujun Li, Michel Galley, Chris Brockett, Mengdi Wang, Jianfeng Gao |
| Abstract | Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models from the perspectives of coherence and cohesion. In this work, we propose a new neural language model that is equipped with two neural discriminators which provide feedback signals at the levels of sentence (cohesion) and paragraph (coherence). Our model is trained using a simple yet efficient variant of policy gradient, called negative-critical sequence training, which is proposed to eliminate the need of training a separate critic for estimating baseline. Results demonstrate the effectiveness of our approach, showing improvements over the strong baseline – recurrent attention-based bidirectional MLE-trained neural language model. |
| Tasks | Language Modelling, Text Generation |
| Published | 2018-11-01 |
| URL | https://arxiv.org/abs/1811.00511v2 |
| https://arxiv.org/pdf/1811.00511v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-birds-eye-view-on-coherence-and-a-worms-eye |
| Repo | |
| Framework | |
Bayesian Mean-parameterized Nonnegative Binary Matrix Factorization
| Title | Bayesian Mean-parameterized Nonnegative Binary Matrix Factorization |
| Authors | Alberto Lumbreras, Louis Filstroff, Cédric Févotte |
| Abstract | Binary data matrices can represent many types of data such as social networks, votes or gene expression. In some cases, the analysis of binary matrices can be tackled with nonnegative matrix factorization (NMF), where the observed data matrix is approximated by the product of two smaller nonnegative matrices. In this context, probabilistic NMF assumes a generative model where the data is usually Bernoulli-distributed. Often, a link function is used to map the factorization to the $[0,1]$ range, ensuring a valid Bernoulli mean parameter. However, link functions have the potential disadvantage to lead to uninterpretable models. Mean-parameterized NMF, on the contrary, overcomes this problem. We propose a unified framework for Bayesian mean-parameterized nonnegative binary matrix factorization models (NBMF). We analyze three models which correspond to three possible constraints that respect the mean-parametrization without the need for link functions. Furthermore, we derive a novel collapsed Gibbs sampler and a collapsed variational algorithm to infer the posterior distribution of the factors. Next, we extend the proposed models to a nonparametric setting where the number of used latent dimensions is automatically driven by the observed data. We analyze the performance of our NBMF methods in multiple datasets for different tasks such as dictionary learning and prediction of missing data. Experiments show that our methods provide similar or superior results than the state of the art, while automatically detecting the number of relevant components. |
| Tasks | Dictionary Learning |
| Published | 2018-12-17 |
| URL | https://arxiv.org/abs/1812.06866v2 |
| https://arxiv.org/pdf/1812.06866v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-mean-parameterized-nonnegative |
| Repo | |
| Framework | |
Semi-supervised Learning: Fusion of Self-supervised, Supervised Learning, and Multimodal Cues for Tactical Driver Behavior Detection
| Title | Semi-supervised Learning: Fusion of Self-supervised, Supervised Learning, and Multimodal Cues for Tactical Driver Behavior Detection |
| Authors | Athma Narayanan, Yi-Ting Chen, Srikanth Malla |
| Abstract | In this paper, we presented a preliminary study for tactical driver behavior detection from untrimmed naturalistic driving recordings. While supervised learning based detection is a common approach, it suffers when labeled data is scarce. Manual annotation is both time-consuming and expensive. To emphasize this problem, we experimented on a 104-hour real-world naturalistic driving dataset with a set of predefined driving behaviors annotated. There are three challenges in the dataset. First, predefined driving behaviors are sparse in a naturalistic driving setting. Second, the distribution of driving behaviors is long-tail. Third, a huge intra-class variation is observed. To address these issues, recent self-supervised and supervised learning and fusion of multimodal cues are leveraged into our architecture design. Preliminary experiments and discussions are reported. |
| Tasks | |
| Published | 2018-07-02 |
| URL | http://arxiv.org/abs/1807.00864v1 |
| http://arxiv.org/pdf/1807.00864v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-fusion-of-self |
| Repo | |
| Framework | |
SegET: Deep Neural Network with Rich Contextual Features for Cellular Structures Segmentation in Electron Tomography Image
| Title | SegET: Deep Neural Network with Rich Contextual Features for Cellular Structures Segmentation in Electron Tomography Image |
| Authors | Enze Zhang, Fa Zhang, Zhiyong Liu, Xiaohua Wan, Lifa Zhu |
| Abstract | Electron tomography (ET) allows high-resolution reconstructions of macromolecular complexes at nearnative state. Cellular structures segmentation in the reconstruction data from electron tomographic images is often required for analyzing and visualizing biological structures, making it a powerful tool for quantitative descriptions of whole cell structures and understanding biological functions. However, these cellular structures are rather difficult to automatically separate or quantify from view owing to complex molecular environment and the limitations of reconstruction data of ET. In this paper, we propose a single end-to-end deep fully-convolutional semantic segmentation network dubbed SegET with rich contextual features which fully exploitsthe multi-scale and multi-level contextual information and reduces the loss of details of cellular structures in ET images. We trained and evaluated our network on the electron tomogram of the CTL Immunological Synapse from Cell Image library. Our results demonstrate that SegET can automatically segment accurately and outperform all other baseline methods on each individual structure in our ET dataset. |
| Tasks | Electron Tomography, Semantic Segmentation |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11729v1 |
| http://arxiv.org/pdf/1811.11729v1.pdf | |
| PWC | https://paperswithcode.com/paper/seget-deep-neural-network-with-rich |
| Repo | |
| Framework | |
