With the advent of Deep Learning (DL) techniques, especially Generative Adversarial Networks (GANs), data augmentation and generation are quickly evolving domains that have raised much interest recently. However, the DL techniques are data demanding and since, medical data is not easily accessible, they suffer from data insufficiency. To deal with this limitation, different data augmentation techniques are used. Here, we propose a novel unsupervised data-driven approach for data augmentation that can generate 2D Computed Tomography (CT) images using a simple GAN. The generated CT images have good global and local features of a real CT image and can be used to augment the training datasets for effective learning. In this proof-of-concept study, we show that our proposed solution using GANs is able to capture some of the global and local CT variabilities. Our network is able to generate visually realistic CT images and we aim to further enhance its output by scaling it to a higher resolution and potentially from 2D to 3D.

In recent years, deep neural networks have achieved great success in the field of computer vision. However, it is still a big challenge to deploy these deep models on resource-constrained embedded devices such as mobile robots, smart phones and so on. Therefore, network compression for such platforms is a reasonable solution to reduce memory consumption and computation complexity. In this paper, a novel channel pruning method based on genetic algorithm is proposed to compress very deep Convolution Neural Networks (CNNs). Firstly, a pre-trained CNN model is pruned layer by layer according to the sensitivity of each layer. After that, the pruned model is fine-tuned based on knowledge distillation framework. These two improvements significantly decrease the model redundancy with less accuracy drop. Channel selection is a combinatorial optimization problem that has exponential solution space. In order to accelerate the selection process, the proposed method formulates it as a search problem, which can be solved efficiently by genetic algorithm. Meanwhile, a two-step approximation fitness function is designed to further improve the efficiency of genetic process. The proposed method has been verified on three benchmark datasets with two popular CNN models: VGGNet and ResNet. On the CIFAR-100 and ImageNet datasets, our approach outperforms several state-of-the-art methods. On the CIFAR-10 and SVHN datasets, the pruned VGGNet achieves better performance than the original model with 8 times parameters compression and 3 times FLOPs reduction.

In this paper, we propose to combine imitation and reinforcement learning via the idea of reward shaping using an oracle. We study the effectiveness of the near-optimal cost-to-go oracle on the planning horizon and demonstrate that the cost-to-go oracle shortens the learner's planning horizon as function of its accuracy: a globally optimal oracle can shorten the planning horizon to one, leading to a one-step greedy Markov Decision Process which is much easier to optimize, while an oracle that is far away from the optimality requires planning over a longer horizon to achieve near-optimal performance. Hence our new insight bridges the gap and interpolates between imitation learning and reinforcement learning. Motivated by the above mentioned insights, we propose Truncated HORizon Policy Search (THOR), a method that focuses on searching for policies that maximize the total reshaped reward over a finite planning horizon when the oracle is sub-optimal. We experimentally demonstrate that a gradient-based implementation of THOR can achieve superior performance compared to RL baselines and IL baselines even when the oracle is sub-optimal.

Molecular structure-property relationships are the key to molecular engineering for materials and drug discovery. The rise of deep learning offers a new viable solution to elucidate the structure-property relationships directly from chemical data. Here we show that graph attention networks can greatly improve performance of the deep learning for chemistry. The attention mechanism enables to distinguish atoms in different environments and thus to extract important structural features determining target properties. We demonstrated that our model can detect appropriate features for molecular polarity, solubility, and energy. Interestingly, it identified two distinct parts of molecules as essential structural features for high photovoltaic efficiency, each of which coincided with the area of donor and acceptor orbitals in charge-transfer excitations, respectively. As a result, it could accurately predict molecular properties. Moreover, the resultant latent space was well-organized such that molecules with similar properties were closely located, which is critical for successful molecular engineering.

We prove stable recurrent neural networks are well approximated by feed-forward networks for the purpose of both inference and training by gradient descent. Our result applies to a broad range of non-linear recurrent neural networks under a natural stability condition, which we observe is also necessary. Complementing our theoretical findings, we verify the conclusions of our theory on both real and synthetic tasks. Furthermore, we demonstrate recurrent models satisfying the stability assumption of our theory can have excellent performance on real sequence learning tasks.

Model-based deep reinforcement learning (DRL) algorithm uses the sampled data from a real environment to learn the underlying system dynamics to construct an approximate cyber environment. By using the synthesized data generated from the cyber environment to train the target controller, the training cost can be reduced significantly. In current research, issues such as the applicability of approximate model and the strategy to sample and train from the real and cyber environment have not been fully investigated. To address these issues, we propose to utilize an intelligent trainer to properly use the approximate model and control the sampling and training procedure in the model-based DRL. To do so, we package the training process of a model-based DRL as a standard RL environment, and design an RL trainer to control the training process. The trainer has three control actions: the first action controls where to sample in the real and cyber environment; the second action determines how many data should be sampled from the cyber environment and the third action controls how many times the cyber data should be used to train the target controller. These actions would be controlled manually if without the trainer. The proposed framework is evaluated on five different tasks of OpenAI gym and the test results show that the proposed trainer achieves significant better performance than a fixed parameter model-based RL baseline algorithm. In addition, we compare the performance of the intelligent trainer to a random trainer and prove that the intelligent trainer can indeed learn on the fly. The proposed training framework can be extended to more control actions with more sophisticated trainer design to further reduce the tweak cost of model-based RL algorithms.

We propose an adversarial learning approach to the generation of multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN's generator is a modified hierarchical recurrent encoder-decoder network (HRED) and the discriminator is a word-level bidirectional RNN that shares context and word embedding with the generator. During inference, noise samples conditioned on the dialogue history are used to perturb the generator's latent space to generate several possible responses. The final response is the one ranked best by the discriminator. The hredGAN shows major advantages over existing methods: (1) it generalizes better than networks trained using only the log-likelihood criterion, and (2) it generates longer, more informative and more diverse responses with high utterance and topic relevance even with limited training data. This superiority is demonstrated on the Movie triples and Ubuntu dialogue datasets in terms of perplexity, BLEU, ROUGE and Distinct n-gram scores.

Neuroimaging data analysis often involves \emph{a-priori} selection of data features to study the underlying neural activity. Since this could lead to sub-optimal feature selection and thereby prevent the detection of subtle patterns in neural activity, data-driven methods have recently gained popularity for optimizing neuroimaging data analysis pipelines and thereby, improving our understanding of neural mechanisms. In this context, we developed a deep convolutional architecture that can identify discriminating patterns in neuroimaging data and applied it to electroencephalography (EEG) recordings collected from 25 subjects performing a hand motor task before and after a rest period or a bout of exercise. The deep network was trained to classify subjects into exercise and control groups based on differences in their EEG signals. Subsequently, we developed a novel method termed the cue-combination for Class Activation Map (ccCAM), which enabled us to identify discriminating spatio-temporal features within definite frequency bands (23--33 Hz) and assess the effects of exercise on the brain. Additionally, the proposed architecture allowed the visualization of the differences in the propagation of underlying neural activity across the cortex between the two groups, for the first time in our knowledge. Our results demonstrate the feasibility of using deep network architectures for neuroimaging analysis in different contexts such as, for the identification of robust brain biomarkers to better characterize and potentially treat neurological disorders.

Dating and romantic relationships not only play a huge role in our personal lives but also collectively influence and shape society. Today, many romantic partnerships originate from the Internet, signifying the importance of technology and the web in modern dating. In this paper, we present a text-based computational approach for estimating the relationship compatibility of two users on social media. Unlike many previous works that propose reciprocal recommender systems for online dating websites, we devise a distant supervision heuristic to obtain real world couples from social platforms such as Twitter. Our approach, the CoupleNet is an end-to-end deep learning based estimator that analyzes the social profiles of two users and subsequently performs a similarity match between the users. Intuitively, our approach performs both user profiling and match-making within a unified end-to-end framework. CoupleNet utilizes hierarchical recurrent neural models for learning representations of user profiles and subsequently coupled attention mechanisms to fuse information aggregated from two users. To the best of our knowledge, our approach is the first data-driven deep learning approach for our novel relationship recommendation problem. We benchmark our CoupleNet against several machine learning and deep learning baselines. Experimental results show that our approach outperforms all approaches significantly in terms of precision. Qualitative analysis shows that our model is capable of also producing explainable results to users.

While knowledge representation and reasoning are considered the keys for human-level artificial intelligence, connectionist networks have been shown successful in a broad range of applications due to their capacity for robust learning and flexible inference under uncertainty. The idea of representing symbolic knowledge in connectionist networks has been well-received and attracted much attention from research community as this can establish a foundation for integration of scalable learning and sound reasoning. In previous work, there exist a number of approaches that map logical inference rules with feed-forward propagation of artificial neural networks (ANN). However, the discriminative structure of an ANN requires the separation of input/output variables which makes it difficult for general reasoning where any variables should be inferable. Other approaches address this issue by employing generative models such as symmetric connectionist networks, however, they are difficult and convoluted. In this paper we propose a novel method to represent propositional formulas in restricted Boltzmann machines which is less complex, especially in the cases of logical implications and Horn clauses. An integration system is then developed and evaluated in real datasets which shows promising results.