https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

Classification is one of the most popular topics in hyperspectral remote sensing. In the last two decades, a huge number of methods were proposed to deal with the hyperspectral data classification problem. However, most of them do not hierarchically extract deep features. In this paper, the concept of deep learning is introduced into hyperspectral data classification for the first time. First, we verify the eligibility of stacked autoencoders by following classical spectral information-based classification. Second, a new way of classifying with spatial-dominated information is proposed. We then propose a novel deep learning framework to merge the two features, from which we can get the highest classification accuracy. The framework is a hybrid of principle component analysis (PCA), deep learning architecture, and logistic regression. Specifically, as a deep learning architecture, stacked autoencoders are aimed to get useful high-level features. Experimental results with widely-used hyperspectral data indicate that classifiers built in this deep learning-based framework provide competitive performance. In addition, the proposed joint spectral-spatial deep neural network opens a new window for future research, showcasing the deep learning-based methods' huge potential for accurate hyperspectral data classification.

Deep Learning-Based Classification of Hyperspectral Data

Due to the advantages of deep learning, in this paper, a regularized deep feature extraction (FE) method is presented for hyperspectral image (HSI) classification using a convolutional neural network (CNN). The proposed approach employs several convolutional and pooling layers to extract deep features from HSIs, which are nonlinear, discriminant, and invariant. These features are useful for image classification and target detection. Furthermore, in order to address the common issue of imbalance between high dimensionality and limited availability of training samples for the classification of HSI, a few strategies such as L2 regularization and dropout are investigated to avoid overfitting in class data modeling. More importantly, we propose a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery. Finally, in order to further improve the performance, a virtual sample enhanced method is proposed. The proposed approaches are carried out on three widely used hyperspectral data sets: Indian Pines, University of Pavia, and Kennedy Space Center. The obtained results reveal that the proposed models with sparse constraints provide competitive results to state-of-the-art methods. In addition, the proposed deep FE opens a new window for further research.

/pdf/deep-feature-extraction-and-classification-of-hyperspectral-4p21mou7rr.pdf

Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

How Does the Brain Solve Visual Object Recognition

Computational modeling of the primate visual system yields insights of potential relevance to some of the challenges that computer vision is facing, such as object recognition and categorization, motion detection and activity recognition, or vision-based navigation and manipulation. This paper reviews some functional principles and structures that are generally thought to underlie the primate visual cortex, and attempts to extract biological principles that could further advance computer vision research. Organized for a computer vision audience, we present functional principles of the processing hierarchies present in the primate visual system considering recent discoveries in neurophysiology. The hierarchical processing in the primate visual system is characterized by a sequence of different levels of processing (on the order of 10) that constitute a deep hierarchy in contrast to the flat vision architectures predominantly used in today's mainstream computer vision. We hope that the functional description of the deep hierarchies realized in the primate visual system provides valuable insights for the design of computer vision algorithms, fostering increasingly productive interaction between biological and computer vision research.

/pdf/deep-hierarchies-in-the-primate-visual-cortex-what-can-we-2edoi6tvp4.pdf

Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?

The anterior part of the macaque inferior temporal cortex, area TE, occupies a large portion of the temporal lobe and is critical for object recognition. Thus far, no relation between anatomical subdivisions of TE and neuronal selectivity has been described. Here, we present evidence that neurons selective for three-dimensional (3D) shape are concentrated in the lower bank of the superior temporal sulcus, whereas neurons in lateral TE are generally unselective for 3D shape, though equally selective for 2D shape. These findings reveal that TE consists of at least two distinct areas, one of which processes a specific object property.

/pdf/selectivity-for-3d-shape-that-reveals-distinct-areas-within-4o2qu8z4ab.pdf

Selectivity for 3D Shape That Reveals Distinct Areas Within Macaque Inferior Temporal Cortex

Anterior regions of monkey parietal cortex process visual 3D shape.

Three-dimensional shape coding in inferior temporal cortex

Real-world objects are three-dimensional (3D). Yet, it is unknown whether the neurons of the inferior temporal cortex, which is critical for object recognition, are selective for the 3D shape of objects. We tested for such selectivity by comparing responses to stereo-defined curved 3D shapes derived from identical pairs of monocular images. More than one-third of macaque inferior temporal neurons were selective for 3D shape. In the vast majority of those neurons, this selectivity depended on the global binocular disparity gradient and not on the local disparity. Thus, inferior temporal cortex processes not only two-dimensional but also 3D shape information.

Peter Janssen

Papers

Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?

Selectivity for 3D Shape That Reveals Distinct Areas Within Macaque Inferior Temporal Cortex

Anterior regions of monkey parietal cortex process visual 3D shape.

Three-dimensional shape coding in inferior temporal cortex

Macaque inferior temporal neurons are selective for disparity-defined three-dimensional shapes.