to

### Regularizing Recurrent Networks - On Injected Noise and Norm-based Methods

Advancements in parallel processing have lead to a surge in multilayer perceptrons' (MLP) applications and deep learning in the past decades. Recurrent Neural Networks (RNNs) give additional representational power to feedforward MLPs by providing a way to treat sequential data. However, RNNs are hard to train using conventional error backpropagation methods because of the difficulty in relating inputs over many time-steps. Regularization approaches from MLP sphere, like dropout and noisy weight training, have been insufficiently applied and tested on simple RNNs. Moreover, solutions have been proposed to improve convergence in RNNs but not enough to improve the long term dependency remembering capabilities thereof. In this study, we aim to empirically evaluate the remembering and generalization ability of RNNs on polyphonic musical datasets. The models are trained with injected noise, random dropout, norm-based regularizers and their respective performances compared to well-initialized plain RNNs and advanced regularization methods like fast-dropout. We conclude with evidence that training with noise does not improve performance as conjectured by a few works in RNN optimization before ours.

### Rethinking Full Connectivity in Recurrent Neural Networks

Recurrent neural networks (RNNs) are omnipresent in sequence modeling tasks. Practical models usually consist of several layers of hundreds or thousands of neurons which are fully connected. This places a heavy computational and memory burden on hardware, restricting adoption in practical low-cost and low-power devices. Compared to fully convolutional models, the costly sequential operation of RNNs severely hinders performance on parallel hardware. This paper challenges the convention of full connectivity in RNNs. We study structurally sparse RNNs, showing that they are well suited for acceleration on parallel hardware, with a greatly reduced cost of the recurrent operations as well as orders of magnitude less recurrent weights. Extensive experiments on challenging tasks ranging from language modeling and speech recognition to video action recognition reveal that structurally sparse RNNs achieve competitive performance as compared to fully-connected networks. This allows for using large sparse RNNs for a wide range of real-world tasks that previously were too costly with fully connected networks.

### How Robust are Deep Neural Networks?

Convolutional and Recurrent, deep neural networks have been successful in machine learning systems for computer vision, reinforcement learning, and other allied fields. However, the robustness of such neural networks is seldom apprised, especially after high classification accuracy has been attained. In this paper, we evaluate the robustness of three recurrent neural networks to tiny perturbations, on three widely used datasets, to argue that high accuracy does not always mean a stable and a robust (to bounded perturbations, adversarial attacks, etc.) system. Especially, normalizing the spectrum of the discrete recurrent network to bound the spectrum (using power method, Rayleigh quotient, etc.) on a unit disk produces stable, albeit highly non-robust neural networks. Furthermore, using the $\epsilon$-pseudo-spectrum, we show that training of recurrent networks, say using gradient-based methods, often result in non-normal matrices that may or may not be diagonalizable. Therefore, the open problem lies in constructing methods that optimize not only for accuracy but also for the stability and the robustness of the underlying neural network, a criterion that is distinct from the other.

### Persistent RNNs

At SVAIL (Silicon Valley AI Lab), our mission is to create AI technology that lets us have a significant impact on hundreds of millions of people. We believe that a good way to do this is to improve the accuracy of speech recognition by scaling up deep learning algorithms on larger datasets than what has been done in the past. These algorithms are very compute intensive, so much so that the memory capacity and computational throughput of our systems limits the amount of data and the size of the neural network that we can train. So a big challenge is figuring out how to run deep learning algorithms more efficiently. Doing so would allow us to train bigger models on bigger datasets, which so far has translated into better speech recognition accuracy.

### Orthogonal Recurrent Neural Networks with Scaled Cayley Transform

Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and in some cases, exceed the capabilities of Long Short-Term Memory networks (LSTMs). We propose a simpler and novel update scheme to maintain orthogonal recurrent weight matrices without using complex valued matrices. This is done by parametrizing with a skew-symmetric matrix using the Cayley transform. Such a parametrization is unable to represent matrices with negative one eigenvalues, but this limitation is overcome by scaling the recurrent weight matrix by a diagonal matrix consisting of ones and negative ones. The proposed training scheme involves a straightforward gradient calculation and update step. In several experiments, the proposed scaled Cayley orthogonal recurrent neural network (scoRNN) achieves superior results with fewer trainable parameters than other unitary RNNs.