arXiv subjects

Yujia Li

Publications and source records attributed to Yujia Li.

65 records · Page 4Linked to original sources

arXiv2017

All-optical wavelength-tunable narrow-linewidth fiber laser

Parameter regulations of narrow-linewidth fiber lasers in frequency domain has drawn considerable interests for widespread applications in the light quantum computing, precise coherent detection, and generation of micro-waves. All-optical methods provide compact, precise and fast accesses to achieving these lasers with wavelength-tunability. Here, the optical-thermal effects of graphene is utilized to precisely control operations of free-running lasers with a tuning speed of 140 MHz/ms. Assisted by the single-longitude-mode operation and linewidth suppression of stimulated Brillouin backscattering, we obtain an optical-controllable ~750 Hz fiber laser with a wavelength-tuning range of 3.7 nm.

physics.optics↗

arXiv2017

Gated Graph Sequence Neural Networks

Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modify to use gated recurrent units and modern optimization techniques and then extend to output sequences. The result is a flexible and broadly useful class of neural network models that has favorable inductive biases relative to purely sequence-based models (e.g., LSTMs) when the problem is graph-structured. We demonstrate the capabilities on some simple AI (bAbI) and graph algorithm learning tasks. We then show it achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures.

cs.LG↗

arXiv2017

The Variational Fair Autoencoder

We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. Our model is based on a variational autoencoding architecture with priors that encourage independence between sensitive and latent factors of variation. Any subsequent processing, such as classification, can then be performed on this purged latent representation. To remove any remaining dependencies we incorporate an additional penalty term based on the "Maximum Mean Discrepancy" (MMD) measure. We discuss how these architectures can be efficiently trained on data and show in experiments that this method is more effective than previous work in removing unwanted sources of variation while maintaining informative latent representations.

stat.ML↗

arXiv2017

Learning model-based planning from scratch

Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model can be used to evaluate a plan, it does not prescribe how to construct a plan. Here we introduce the "Imagination-based Planner", the first model-based, sequential decision-making agent that can learn to construct, evaluate, and execute plans. Before any action, it can perform a variable number of imagination steps, which involve proposing an imagined action and evaluating it with its model-based imagination. All imagined actions and outcomes are aggregated, iteratively, into a "plan context" which conditions future real and imagined actions. The agent can even decide how to imagine: testing out alternative imagined actions, chaining sequences of actions together, or building a more complex "imagination tree" by navigating flexibly among the previously imagined states using a learned policy. And our agent can learn to plan economically, jointly optimizing for external rewards and computational costs associated with using its imagination. We show that our architecture can learn to solve a challenging continuous control problem, and also learn elaborate planning strategies in a discrete maze-solving task. Our work opens a new direction toward learning the components of a model-based planning system and how to use them.

cs.AI↗

arXiv2017

Dualing GANs

Generative adversarial nets (GANs) are a promising technique for modeling a distribution from samples. It is however well known that GAN training suffers from instability due to the nature of its maximin formulation. In this paper, we explore ways to tackle the instability problem by dualizing the discriminator. We start from linear discriminators in which case conjugate duality provides a mechanism to reformulate the saddle point objective into a maximization problem, such that both the generator and the discriminator of this 'dualing GAN' act in concert. We then demonstrate how to extend this intuition to non-linear formulations. For GANs with linear discriminators our approach is able to remove the instability in training, while for GANs with nonlinear discriminators our approach provides an alternative to the commonly used GAN training algorithm.

cs.LG↗

arXiv2017

Optical-controlled wavelength-tunable Q-switched mode-locked fiber laser based on graphene-deposited micro-FBG

We report a wavelength-tunable Q-switched mode-locked fiber laser based on a compact optical tuning device, which is fabricated by coating single-layer graphene on the surface of micro-fiber Bragg grating (MFBG). Based on thermal-optical effect through evanescent interaction between graphene and MFBG, the center wavelength of MFBG can be accurately controlled by adjusting power of an external laser. By inserting the fabricated device into a compact fiber laser cavity mode-locked by single-wall carbon nanotubes, stable Q-switched mode-locked pulse is generated. Experimental results show that the wavelength can be precisely optical-tuned from 1550.1 nm to 1551.9 nm with a linear sensitivity of 6.3 pm/mW. Such an optical-controlled wavelength-tunable Q-switched mode-locked fiber laser may find potential applications in all-optical computing, all-optical logic gating and generation of microwave source.

physics.optics↗

arXiv2017

Understanding the Effective Receptive Field in Deep Convolutional Neural Networks

We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field, and show that it both has a Gaussian distribution and only occupies a fraction of the full theoretical receptive field. We analyze the effective receptive field in several architecture designs, and the effect of nonlinear activations, dropout, sub-sampling and skip connections on it. This leads to suggestions for ways to address its tendency to be too small.

cs.CV↗

arXiv2015

Watt-level, all-fiber, ultrafast Er/Yb-codoped double-clad fiber laser mode-locked by reduced graphene oxide interacting with a weak evanescent field

We propose a Watt-level, all-fiber, ultrafast Er/Yb-codoped double-clad fiber laser passively mode-locked by reduced graphene oxide (rGO) interacting with a weak evanescent field of photonic crystal fiber (PCF). The rGO solution is filled into the cladding holes of the PCF based on total reflection, and after evaporation, the rGO flakes bear only 1/107 of the total energy in laser system, which enhances the thermal damage threshold and decreases the accumulated nonlinearity. By incorporating the saturable absorber into an Er/Yb-codoped fiber ring cavity, stable conventional soliton with a duration of 573 fs is generated, and a average output power up to 1.14 W is obtained.

physics.optics↗

arXiv2015

Generative Moment Matching Networks

We consider the problem of learning deep generative models from data. We formulate a method that generates an independent sample via a single feedforward pass through a multilayer perceptron, as in the recently proposed generative adversarial networks (Goodfellow et al., 2014). Training a generative adversarial network, however, requires careful optimization of a difficult minimax program. Instead, we utilize a technique from statistical hypothesis testing known as maximum mean discrepancy (MMD), which leads to a simple objective that can be interpreted as matching all orders of statistics between a dataset and samples from the model, and can be trained by backpropagation. We further boost the performance of this approach by combining our generative network with an auto-encoder network, using MMD to learn to generate codes that can then be decoded to produce samples. We show that the combination of these techniques yields excellent generative models compared to baseline approaches as measured on MNIST and the Toronto Face Database.

cs.LG↗

arXiv2014

Learning unbiased features

A key element in transfer learning is representation learning; if representations can be developed that expose the relevant factors underlying the data, then new tasks and domains can be learned readily based on mappings of these salient factors. We propose that an important aim for these representations are to be unbiased. Different forms of representation learning can be derived from alternative definitions of unwanted bias, e.g., bias to particular tasks, domains, or irrelevant underlying data dimensions. One very useful approach to estimating the amount of bias in a representation comes from maximum mean discrepancy (MMD) [5], a measure of distance between probability distributions. We are not the first to suggest that MMD can be a useful criterion in developing representations that apply across multiple domains or tasks [1]. However, in this paper we describe a number of novel applications of this criterion that we have devised, all based on the idea of developing unbiased representations. These formulations include: a standard domain adaptation framework; a method of learning invariant representations; an approach based on noise-insensitive autoencoders; and a novel form of generative model.

cs.LG↗

arXiv2014

Mean-Field Networks

The mean field algorithm is a widely used approximate inference algorithm for graphical models whose exact inference is intractable. In each iteration of mean field, the approximate marginals for each variable are updated by getting information from the neighbors. This process can be equivalently converted into a feedforward network, with each layer representing one iteration of mean field and with tied weights on all layers. This conversion enables a few natural extensions, e.g. untying the weights in the network. In this paper, we study these mean field networks (MFNs), and use them as inference tools as well as discriminative models. Preliminary experiment results show that MFNs can learn to do inference very efficiently and perform significantly better than mean field as discriminative models.

cs.LG↗