deep learning


Deep learning is a subset of machine learning in artificial intelligence (AI) that has networks capable of learning unsupervised from data that is unstructured or unlabeled. Also known as deep neural learning or deep neural network

Deep learning is a class of machine learning algorithms that uses multiple layers to progressively extract higher level features from the raw input. For example, in image processing, lower layers may identify edges, while higher layers may identify the concepts relevant to a human such as digits or letters or faces.

Multimodal deep learning
free download

Deep networks have been successfully applied to unsupervised feature learning for single modalities (eg, text, images or audio). In this work, we propose a novel application of deep networks to learn features over multiple modalities. We present a series of tasks for

Deep learning with limited numerical precision
free download

Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of lowprecision fixed-point

Deep learning via hessian-free optimization.
free download

Page 1. Deep Learning via Hessian-free Optimization James Martens University of Toronto August 13 UNIVERSITY OF TORONTO Computer Science Page 6. Gradient descent is bad at deep learning (cont.) Two hypotheses for why gradient

On the importance of initialization and momentum in deep learning
free download

Deep and recurrent neural networks (DNNs and RNNs respectively) are powerful models that were considered to be almost impossible to train using stochastic gradient descent with momentum. In this paper, we show that when stochastic gradient descent with momentum

Learning transferable features with deep adaptation networks
free download

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops

Neural networks and deep learning
free download

Neural networks are one of the most beautiful programming paradigms ever invented. In the conventional approach to programming, we tell the computer what to do, breaking big problems up into many small, precisely defined tasks that the computer can easily perform

Deep learning of representations for unsupervised and transfer learning
free download

Deep learning algorithms seek to exploit the unknown structure in the input distribution in order to discover good representations, often at multiple levels, with higher-level learned features defined in terms of lower-level features. The objective is to make these higherlevel

Deep learning with COTS HPC systems
free download

Scaling up deep learning algorithms has been shown to lead to increased performance in benchmark tasks and to enable discovery of complex high-level features. Recent efforts to train extremely large networks (with over 1 billion parameters) have relied on cloudlike

Domain adaptation for large-scale sentiment classification: A deep learning approach
free download

The exponential increase in the availability of online reviews and recommendations makes sentiment classification an interesting topic in academic and industrial research. Reviews can span so many different domains that it is difficult to gather annotated training data for all

Chainer: a next-generation open source framework for deep learning
free download

Software frameworks for neural networks play key roles in the development and application of deep learning methods. However, as new types of deep learning models are developed, existing frameworks designed for convolutional neural networks are becoming less useful. In

Dropout as a bayesian approximation: Representing model uncertainty in deep learning
free download

Deep learning tools have gained tremendous attention in applied machine learning . However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about

Deep machine learning -a new frontier in artificial intelligence research
free download

Mimicking the efficiency and robustness by which the human brain represents information has been a core challenge in artificial intelligence research for decades. Humans are exposed to myriad of sensory data received every second of the day and are somehow able

Convolutional-recursive deep learning for 3d object classification
free download

Recent advances in 3D sensing technologies make it possible to easily record color and depth images which together can improve object recognition. Most current methods rely on very well-designed features for this new 3D modality. We introduce a model based on a

Deep learning
free download

Insufficient depth can hurt: Depth 2 can be enough but with a price (eg the required number of nodes grow very large) The brain has a deep architecture: Hierarchical feature representation (eg Image: pixel → edge → object part → object; Text: character → word → phrase →

Uncertainty in deep learning
free download

Deep learning has attracted tremendous attention from researchers in various fields of information engineering such as AI, computer vision, and language processing [Kalchbrenner and Blunsom; Krizhevsky et al.; Mnih et al.], but also from

Deep kernel learning
free download

We introduce scalable deep kernels, which combine the structural properties of deep learning architectures with the nonparametric flexibility of kernel methods. Specifically, we transform the inputs of a spectral mixture base kernel with a deep architecture, using local

Learning features from music audio with deep belief networks.
free download

Feature extraction is a crucial part of many MIR tasks. In this work, we present a system that can automatically extract relevant features from audio for a given task. The feature extraction system consists of a Deep Belief Network (DBN) on Discrete Fourier Transforms (DFTs) of

Learning deep structured models
free download

Many problems in real-world applications involve predicting several random variables that are statistically related. Markov random fields (MRFs) are a great mathematical tool to encode such dependencies. The goal of this paper is to combine MRFs with deep learning

Unsupervised feature learning and deep learning : A review and new perspectives
free download

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although domain

Low precision storage for deep learning
free download

We train a set of state of the art neural networks, the Maxout networks (Goodfellow et al., 2013a), on three benchmark datasets: the MNIST, CIFAR10 and SVHN, with three distinct storing formats: floating point, fixed point and dynamic fixed point. For each of those datasets

Deep learning is part of a broader family of machine learning methods based on artificial neural networks. Learning can be supervised, semi-supervised or unsupervised.


COMMENT artificial-intelligence, deep-learning



  • GURU

    Difference between deep learning and machine learning

    Machine learning algorithms almost always require structured data, whereas deep learning networks rely on layers of the ANN (artificial neural networks). Machine learning algorithms are built to “learn” to do things by understanding labeled data, then use it to produce further outputs with more sets of data.


  • FREE IEEE PAPER