User profiles for Wei-Cheng Chang
 | Wei-Cheng ChangApplied Scientist, Amazon Verified email at amazon.com Cited by 4516 |
Modeling long-and short-term temporal patterns with deep neural networks
Multivariate time series forecasting is an important machine learning problem across many
domains, including predictions of solar plant energy output, electricity consumption, and …
domains, including predictions of solar plant energy output, electricity consumption, and …
Mmd gan: Towards deeper understanding of moment matching network
Generative moment matching network (GMMN) is a deep generative model that differs from
Generative Adversarial Network (GAN) by replacing the discriminator in GAN with a two-…
Generative Adversarial Network (GAN) by replacing the discriminator in GAN with a two-…
Deep learning for extreme multi-label text classification
Extreme multi-label text classification (XMTC) refers to the problem of assigning to each
document its most relevant subset of class labels from an extremely large label collection, where …
document its most relevant subset of class labels from an extremely large label collection, where …
Long-range and local circuits for top-down modulation of visual cortex processing
Top-down modulation of sensory processing allows the animal to select inputs most
relevant to current tasks. We found that the cingulate (Cg) region of the mouse frontal cortex …
relevant to current tasks. We found that the cingulate (Cg) region of the mouse frontal cortex …
Basal forebrain circuit for sleep-wake control
The mammalian basal forebrain (BF) has important roles in controlling sleep and wakefulness,
but the underlying neural circuit remains poorly understood. We examined the BF circuit …
but the underlying neural circuit remains poorly understood. We examined the BF circuit …
Pre-training tasks for embedding-based large-scale retrieval
We consider the large-scale query-document retrieval problem: given a query (eg, a question),
return the set of relevant documents (eg, paragraphs containing the answer) from a large …
return the set of relevant documents (eg, paragraphs containing the answer) from a large …
Identification of preoptic sleep neurons using retrograde labelling and gene profiling
In humans and other mammalian species, lesions in the preoptic area of the hypothalamus
cause profound sleep impairment 1 , 2 , 3 , 4 , 5 , indicating a crucial role of the preoptic area …
cause profound sleep impairment 1 , 2 , 3 , 4 , 5 , indicating a crucial role of the preoptic area …
Taming pretrained transformers for extreme multi-label text classification
We consider the extreme multi-label text classification (XMC) problem: given an input text,
return the most relevant labels from a large label collection. For example, the input text could …
return the most relevant labels from a large label collection. For example, the input text could …
Fast multi-resolution transformer fine-tuning for extreme multi-label text classification
Extreme multi-label text classification~(XMC) seeks to find relevant labels from an extreme
large label collection for a given text input. Many real-world applications can be formulated as …
large label collection for a given text input. Many real-world applications can be formulated as …
Organization of long-range inputs and outputs of frontal cortex for top-down control
Long-range projections from the frontal cortex are known to modulate sensory processing in
multiple modalities. Although the mouse has become an increasingly important animal …
multiple modalities. Although the mouse has become an increasingly important animal …