Eligibility traces are an effective technique to accelerate reinforcement learning by smoothly assigning credit to recently visited states. However, their online implementation is incompatible with modern deep reinforcement learning algorithms, which rely heavily on i.i.d. training data and offline learning. We utilize an efficient, recursive method for computing {\lambda}-returns offline that can provide the benefits of eligibility traces to any value-estimation or actor-critic method. We demonstrate how our method can be combined with DQN, DRQN, and A3C to greatly enhance the learning speed of these algorithms when playing Atari 2600 games, even under partial observability. Our results indicate several-fold improvements to sample efficiency on Seaquest and Q*bert. We expect similar results for other algorithms and domains not considered here, including those with continuous actions.

The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems. The field of quantitative analysis has been slowly adapting the new methods to its problems, but due to problems such as the non-stationary nature of financial data, significant challenges must be overcome before DL is fully utilized. In this work a new method to construct stationary features, that allows DL models to be applied effectively, is proposed. These features are thoroughly tested on the task of predicting mid price movements of the Limit Order Book. Several DL models are evaluated, such as recurrent Long Short Term Memory (LSTM) networks and Convolutional Neural Networks (CNN). Finally a novel model that combines the ability of CNNs to extract useful features and the ability of LSTMs' to analyze time series, is proposed and evaluated. The combined model is able to outperform the individual LSTM and CNN models in the prediction horizons that are tested.

The analysis of neuroimaging data poses several strong challenges, in particular, due to its high dimensionality, its strong spatio-temporal correlation and the comparably small sample sizes of the respective datasets. To address these challenges, conventional decoding approaches such as the searchlight reduce the complexity of the decoding problem by considering local clusters of voxels only. Thereby, neglecting the distributed spatial patterns of brain activity underlying many cognitive states. In this work, we introduce the DLight framework, which overcomes these challenges by utilizing a long short-term memory unit (LSTM) based deep neural network architecture to analyze the spatial dependency structure of whole-brain fMRI data. In order to maintain interpretability of the neuroimaging data, we adapt the layer-wise relevance propagation (LRP) method. Thereby, we enable the neuroscientist user to study the learned association of the LSTM between the data and the cognitive state of the individual. We demonstrate the versatility of DLight by applying it to a large fMRI dataset of the Human Connectome Project. We show that the decoding performance of our method scales better with large datasets, and moreover outperforms conventional decoding approaches, while still detecting physiologically appropriate brain areas for the cognitive states classified. We also demonstrate that DLight is able to detect these areas on several levels of data granularity (i.e., group, subject, trial, time point).

Recent progress in deep learning for audio synthesis opens the way to models that directly produce the waveform, shifting away from the traditional paradigm of relying on vocoders or MIDI synthesizers for speech or music generation. Despite their successes, current state-of-the-art neural audio synthesizers such as WaveNet and SampleRNN suffer from prohibitive training and inference times because they are based on autoregressive models that generate audio samples one at a time at a rate of 16kHz. In this work, we study the more computationally efficient alternative of generating the waveform frame-by-frame with large strides. We present SING, a lightweight neural audio synthesizer for the original task of generating musical notes given desired instrument, pitch and velocity. Our model is trained end-to-end to generate notes from nearly 1000 instruments with a single decoder, thanks to a new loss function that minimizes the distances between the log spectrograms of the generated and target waveforms. On the generalization task of synthesizing notes for pairs of pitch and instrument not seen during training, SING produces audio with significantly improved perceptual quality compared to a state-of-the-art autoencoder based on WaveNet as measured by a Mean Opinion Score (MOS), and is about 32 times faster for training and 2, 500 times faster for inference.

Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM (rgcLSTM) architecture that requires a significantly lower parameter budget than a comparable convLSTM. Our reduced-gate model achieves equal or better next-frame(s) prediction accuracy than the original convolutional LSTM while using a smaller parameter budget, thereby reducing training time. We tested our reduced gate modules within a predictive coding architecture on the moving MNIST and KITTI datasets. We found that our reduced-gate model has a significant reduction of approximately 40 percent of the total number of training parameters and a 25 percent redution in elapsed training time in comparison with the standard convolutional LSTM model. This makes our model more attractive for hardware implementation especially on small devices.

Adversarial training is an effective method for improving robustness to adversarial attacks. We show that adversarial training using the Fast Signed Gradient Method can be interpreted as a form of regularization. We implemented a more effective form of adversarial training, which in turn can be interpreted as regularization of the loss in the 2-norm, $\|\nabla_x \ell(x)\|_2$. We obtained further improvements to adversarial robustness, as well as provable robustness guarantees, by augmenting adversarial training with Lipschitz regularization.

Inverse problems in imaging such as denoising, deblurring, superresolution (SR) have been addressed for many decades. In recent years, convolutional neural networks (CNNs) have been widely used for many inverse problem areas. Although their indisputable success, CNNs are not mathematically validated as to how and what they learn. In this paper, we prove that during training, CNN elements solve for inverse problems which are optimum solutions stored as CNN neuron filters. We discuss the necessity of mutual coherence between CNN layer elements in order for a network to converge to the optimum solution. We prove that required mutual coherence can be provided by the usage of residual learning and skip connections. We have set rules over training sets and depth of networks for better convergence, i.e. performance.

An extensive body of empirical research has revealed remarkable regularities in the acquisition, organization, deployment, and neural representation of human semantic knowledge, thereby raising a fundamental conceptual question: what are the theoretical principles governing the ability of neural networks to acquire, organize, and deploy abstract knowledge by integrating across many individual experiences? We address this question by mathematically analyzing the nonlinear dynamics of learning in deep linear networks. We find exact solutions to this learning dynamics that yield a conceptual explanation for the prevalence of many disparate phenomena in semantic cognition, including the hierarchical differentiation of concepts through rapid developmental transitions, the ubiquity of semantic illusions between such transitions, the emergence of item typicality and category coherence as factors controlling the speed of semantic processing, changing patterns of inductive projection over development, and the conservation of semantic similarity in neural representations across species. Thus, surprisingly, our simple neural model qualitatively recapitulates many diverse regularities underlying semantic development, while providing analytic insight into how the statistical structure of an environment can interact with nonlinear deep learning dynamics to give rise to these regularities.

Indicators of Compromise (IOCs) are artifacts observed on a network or in an operating system that can be utilized to indicate a computer intrusion and detect cyber-attacks in an early stage. Thus, they exert an important role in the field of cybersecurity. However, state-of-the-art IOCs detection systems rely heavily on hand-crafted features with expert knowledge of cybersecurity, and require a large amount of supervised training corpora to train an IOC classifier. In this paper, we propose using a neural-based sequence labelling model to identify IOCs automatically from reports on cybersecurity without expert knowledge of cybersecurity. Our work is the first to apply an end-to-end sequence labelling to the task in IOCs identification. By using an attention mechanism and several token spelling features, we find that the proposed model is capable of identifying the low frequency IOCs from long sentences contained in cybersecurity reports. Experiments show that the proposed model outperforms other sequence labelling models, achieving over 88% average F1-score.

It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input. These adversarial examples are crafted, for example, by calculating gradients of a carefully defined loss function with respect to the input. As a countermeasure, some researchers have tried to design robust models by blocking or obfuscating gradients, even in white-box settings. Another line of research proposes introducing a separate detector to attempt to detect adversarial examples. This approach also makes use of gradient obfuscation techniques, for example, to prevent the adversary from trying to fool the detector. In this paper, we introduce stochastic substitute training, a gray-box approach that can craft adversarial examples for defenses which obfuscate gradients. For those defenses that have tried to make models more robust, with our technique, an adversary can craft adversarial examples with no knowledge of the defense. For defenses that attempt to detect the adversarial examples, with our technique, an adversary only needs very limited information about the defense to craft adversarial examples. We demonstrate our technique by applying it against two defenses which make models more robust and two defenses which detect adversarial examples.