Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
54
Deeply learned face representations are sparse, selective, and robust
"... This paper designs a high-performance deep convo-lutional network (DeepID2+) for face recognition. It is learned with the identification-verification supervisory signal. By increasing the dimension of hidden repre-sentations and adding supervision to early convolutional layers, DeepID2+ achieves new ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
new state-of-the-art on LFW and YouTube Faces benchmarks. Through empirical studies, we have discovered three properties of its deep neural activations critical for the high performance: sparsity, selectiveness and robustness. (1) It is observed that neural activations are moderately sparse. Moderate
Robust Soft-Entropy Neural Network Trees
"... We present a new method for the induction of tree-structured recursive partitioning classifiers that use a neural network as the partitioning function at each node in the tree. Our technique is appropriate for pattern recognition tasks with many continuous inputs and a single multivalued nominal out ..."
Abstract
- Add to MetaCart
output. This paper presents two main contributions: 1) a novel objective function called soft entropy, which is used to train each neural net to give the optimal partitioning of the data, and 2) a novel but simple method for removing outliers called iterative re-filtering, which boosts performance
New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence
"... A fundamental open problem in computer vision---determining pose and correspondence between two sets of points in space---is solved with a novel, fast [O(nm)], robust and easily implementable algorithm. The technique works on noisy 2D or 3D point sets that may be of unequal sizes and may differ by n ..."
Abstract
-
Cited by 103 (20 self)
- Add to MetaCart
A fundamental open problem in computer vision---determining pose and correspondence between two sets of points in space---is solved with a novel, fast [O(nm)], robust and easily implementable algorithm. The technique works on noisy 2D or 3D point sets that may be of unequal sizes and may differ
RobustFill: Neural Program Learning under Noisy I/O
"... Abstract The problem of automatically generating a computer program from some specification has been studied since the early days of AI. Recently, two competing approaches for automatic program learning have received significant attention: (1) neural program synthesis, where a neural network is con ..."
Abstract
- Add to MetaCart
is conditioned on input/output (I/O) examples and learns to generate a program, and (2) neural program induction, where a neural network generates new outputs directly using a latent program representation. Here, for the first time, we directly compare both approaches on a large-scale, real-world learning task
Neural Coding and Auditory Perception
"... The long-term goal of this research is to understand the neural mechanisms that mediate the ability of normal-hearing people to understand speech and localize sounds in complex acoustic environments comprising reverberation and competing sound sources. In the past year, we continued work on two rese ..."
Abstract
- Add to MetaCart
research projects: (1) Physiological studies of sound localization in reverberant environments; (2) Spatio-temporal representation of pitch in the auditory nerve and cochlear nucleus. We also started a new project on the dynamic range problem, which impacts all aspects of auditory perception. Sound
Robust Character Recognition using a Hierarchical Bayesian Network
"... Abstract. There is increasing evidence to suggest that the neocortex of the mammalian brain does not consist of a collection of specialised and dedicated cortical architectures, but instead possesses a fairly uniform, hierarchically organised structure. As Mountcastle has observed [1], this uniformi ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
of pattern recognition machine, storing invariant representations of neural input sequences in hierarchical memory structures that both predict sensory input and control behaviour. The first partial proof of concept of Hawkins ’ model was recently developed using a hierarchically organised Bayesian network
Value representation via divisive normalization in parietal cortex
"... Value information is a critical component of the decision-making process. In the lateral intraparietal area (LIP), visuomotor neurons are strongly modulated by reward variables such as expected gain, prior probability, and reward income, suggesting that individual LIP neurons represent the subjectiv ..."
Abstract
- Add to MetaCart
the subjective value of specific saccades [1,2]. In this framework, decision activity across the LIP population initially encodes the values of the available targets; comparison of these values results in action selection and output of choice information to downstream oculomotor structures. Notably, such a
SCREEN: Learning a flat syntactic and semantic spoken language analysis using artificial neural networks
- Journal of Artificial Intelligence Research
, 1997
"... Previous approaches of analyzing spontaneously spoken language often have been based on encoding syntactic and semantic knowledge manually and symbolically. While there has been some progress using statistical or connectionist language models, many current spoken-language systems still use a relativ ..."
Abstract
-
Cited by 23 (10 self)
- Add to MetaCart
an utterance at various syntactic, semantic and dialog levels. Rather than using a deeply structured symbolic analysis, we use a at connectionist analysis. This screening approach aims at supporting speech and language processing by using (1) data-driven learning and (2) robustness of connectionist networks
Visual Pathway Confers Robustness to Clutter and Diverted Attention Report
"... Are objects coded by a small number of neurons or cortical regions that respond preferentially to the object in question, or by more distributed patterns of responses, including neurons or regions that respond only weakly? Distributed codes can represent a larger number of alternative items than spa ..."
Abstract
- Add to MetaCart
MRI response provides robust category information only for objects coded in selective cortical regions and highlight the vulnerability of distributed representations to clutter [1, 2] and the advantages of sparse cortical codes in mitigating clutter costs.
X.: Deep learning multi-view representation for face recognition
, 2014
"... Various factors, such as identities, views (poses), and illuminations, are coupled in face images. Disentangling the identity and view representations is a major challenge in face recognition. Existing face recognition systems either use handcrafted features or learn features discriminatively to imp ..."
Abstract
-
Cited by 3 (2 self)
- Add to MetaCart
robust to view changes. In this sense, human brain has learned and encoded 3D face models from 2D images. To take into account this instinct, this paper proposes a novel deep neural net, named multi-view perceptron (MVP), which can untangle the identity and view features, and infer a full spectrum
Results 1 - 10
of
54
