#### Filter Results:

- Full text PDF available (13)

#### Publication Year

2014

2017

- This year (2)
- Last 5 years (14)
- Last 10 years (14)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Daniel Jiwoong Im, Chris Dongjoo Kim, Hui Jiang, Roland Memisevic
- ArXiv
- 2016

Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual quality. We show that unrolling this gradient-based optimization yields a recurrent computation that creates images by incrementally adding onto a visual “canvas”. We propose a… (More)

Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injected in their stochastic hidden layer, with a regularizer that encourages this noise injection. In this paper, we show that injecting noise both in input and in the stochastic… (More)

- Daniel Jiwoong Im, Michael Tao, Kristin Branson
- ArXiv
- 2016

The training of deep neural networks is a high-dimension optimization problem with respect to the loss function of a model. Unfortunately, these functions are of high dimension and non-convex and hence difficult to characterize. In this paper, we empirically investigate the geometry of the loss functions for state-of-the-art networks with multiple… (More)

- Jan Rudy, Weiguang Ding, Daniel Jiwoong Im, Graham W. Taylor
- ArXiv
- 2014

Regularization is essential when training large neural networks. As deep neural networks can be mathematically interpreted as universal function approximators, they are effective at memorizing sampling noise in the training data. This results in poor generalization to unseen data. Therefore, it is no surprise that a new regularization technique, Dropout,… (More)

We discuss necessary and sufficient conditions for an auto-encoder to define a conservative vector field, in which case it is associated with an energy function akin to the unnormalized log-probability of the data. We show that the conditions for conservativeness are more general than for encoder and decoder weights to be the same (“tied weights”), and that… (More)

- Jiatao Gu, Daniel Jiwoong Im, Victor O. K. Li
- ArXiv
- 2017

Previous neural machine translation models used some heuristic search algorithms (e.g., beam search) in order to avoid solving the maximum a posteriori problem over translation sentences at test time. In this paper, we propose the Gumbel-Greedy Decoding which trains a generative network to predict translation under a trained model. We solve such a problem… (More)

- Daniel Jiwoong Im, He Ma, Chris Dongjoo Kim, Graham W. Taylor
- ArXiv
- 2016

Generative Adversarial Networks (GAN) have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable of generating convincing examples in limited domains, such as low-resolution images. However, they still prove difficult to train in practice and tend to ignore modes of… (More)

- Daniel Jiwoong Im, Graham W. Taylor
- IEEE Geosci. Remote Sensing Lett.
- 2015

In problems where labeled data is scarce, semisupervised learning (SSL) techniques are an attractive framework that can exploit both labeled and unlabeled data. These approaches typically rely on a smoothness assumption such that examples that are similar in input space should also be similar in label space. In many domains, such as remotely sensed… (More)

Auto-encoders are perhaps the best-known non-probabilistic methods for representation learning. They are conceptually simple and easy to train. Recent theoretical work has shed light on their ability to capture manifold structure, and drawn connections to density modeling. This has motivated researchers to seek ways of auto-encoder scoring, which has… (More)

- Daniel Jiwoong Im, Ethan Buchman, Graham W. Taylor
- ArXiv
- 2014

Energy-based models are popular in machine learning due to the elegance of their formulation and their relationship to statistical physics. Among these, the Restricted Boltzmann Machine (RBM), and its staple training algorithm contrastive divergence (CD), have been the prototype for some recent advancements in the unsupervised training of deep neural… (More)