Thomas Kemp

Takuya Narihira, Javier Alonsogarcia, Fabien Cardinaux et al.

While there exist a plethora of deep learning tools and frameworks, the fast-growing complexity of the field brings new demands and challenges, such as more flexible network design, speedy computation on distributed setting, and compatibility between different tools. In this paper, we introduce Neural Network Libraries (https://nnabla.org), a deep learning framework designed from engineer's perspective, with emphasis on usability and compatibility as its core design principles. We elaborate on each of our design principles and its merits, and validate our attempts via experiments.

Lukas Mauch, Stephen Tiedemann, Javier Alonso Garcia et al.

Recently, predictor-based algorithms emerged as a promising approach for neural architecture search (NAS). For NAS, we typically have to calculate the validation accuracy of a large number of Deep Neural Networks (DNNs), what is computationally complex. Predictor-based NAS algorithms address this problem. They train a proxy model that can infer the validation accuracy of DNNs directly from their network structure. During optimization, the proxy can be used to narrow down the number of architectures for which the true validation accuracy must be computed, what makes predictor-based algorithms sample efficient. Usually, we compute the proxy for all DNNs in the network search space and pick those that maximize the proxy as candidates for optimization. However, that is intractable in practice, because the search spaces are often very large and contain billions of network architectures. The contributions of this paper are threefold: 1) We define a sample efficiency gain to compare different predictor-based NAS algorithms. 2) We conduct experiments on the NASBench-101 dataset and show that the sample efficiency of predictor-based algorithms decreases dramatically if the proxy is only computed for a subset of the search space. 3) We show that if we choose the subset of the search space on which the proxy is evaluated in a smart way, the sample efficiency of the original predictor-based algorithm that has access to the full search space can be regained. This is an important step to make predictor-based NAS algorithms useful, in practice.

Giorgio Fabbro, Vladimir Golkov, Thomas Kemp et al.

Modern text-to-speech systems are able to produce natural and high-quality speech, but speech contains factors of variation (e.g. pitch, rhythm, loudness, timbre)\ that text alone cannot contain. In this work we move towards a speech synthesis system that can produce diverse speech renditions of a text by allowing (but not requiring) explicit control over the various factors of variation. We propose a new neural vocoder that offers control of such factors of variation. This is achieved by employing differentiable digital signal processing (DDSP) (previously used only for music rather than speech), which exposes these factors of variation. The results show that the proposed approach can produce natural speech with realistic timbre, and individual factors of variation can be freely controlled.

Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama et al.

Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are network quantization or pruning, which either reduce the word length of the network parameters or remove weights from the network if they are not needed. In this article we discuss a general framework for network reduction which we call `Look-Up Table Quantization` (LUT-Q). For each layer, we learn a value dictionary and an assignment matrix to represent the network weights. We propose a special solver which combines gradient descent and a one-step k-means update to learn both the value dictionaries and assignment matrices iteratively. This method is very flexible: by constraining the value dictionary, many different reduction problems such as non-uniform network quantization, training of multiplierless networks, network pruning or simultaneous quantization and pruning can be implemented without changing the solver. This flexibility of the LUT-Q method allows us to use the same method to train networks for different hardware capabilities.

Stefan Uhlich, Lukas Mauch, Fabien Cardinaux et al.

Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with homogeneous bitwidth for the same size constraint. Since choosing the optimal bitwidths is not straight forward, training methods, which can learn them, are desirable. Differentiable quantization with straight-through gradients allows to learn the quantizer's parameters using gradient methods. We show that a suited parametrization of the quantizer is the key to achieve a stable training and a good final performance. Specifically, we propose to parametrize the quantizer with the step size and dynamic range. The bitwidth can then be inferred from them. Other parametrizations, which explicitly use the bitwidth, consistently perform worse. We confirm our findings with experiments on CIFAR-10 and ImageNet and we obtain mixed precision DNNs with learned quantization parameters, achieving state-of-the-art performance.

Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama et al.

Operating deep neural networks on devices with limited resources requires the reduction of their memory footprints and computational requirements. In this paper we introduce a training method, called look-up table quantization, LUT-Q, which learns a dictionary and assigns each weight to one of the dictionary's values. We show that this method is very flexible and that many other techniques can be seen as special cases of LUT-Q. For example, we can constrain the dictionary trained with LUT-Q to generate networks with pruned weight matrices or restrict the dictionary to powers-of-two to avoid the need for multiplications. In order to obtain fully multiplier-less networks, we also introduce a multiplier-less version of batch normalization. Extensive experiments on image recognition and object detection tasks show that LUT-Q consistently achieves better performance than other methods with the same quantization bitwidth.

Joachim Muth, Stefan Uhlich, Nathanael Perraudin et al.

Music source separation with deep neural networks typically relies only on amplitude features. In this paper we show that additional phase features can improve the separation performance. Using the theoretical relationship between STFT phase and amplitude, we conjecture that derivatives of the phase are a good feature representation opposed to the raw phase. We verify this conjecture experimentally and propose a new DNN architecture which combines amplitude and phase. This joint approach achieves a better signal-to distortion ratio on the DSD100 dataset for all instruments compared to a network that uses only amplitude features. Especially, the bass instrument benefits from the phase information.