Browsing by Subject "Neural Networks (Computer)"

Now showing 1 - 6 of 6
  • Thumbnail Image
    ItemOpen Access
    A framework for integrating the songbird brain.
    (J Comp Physiol A Neuroethol Sens Neural Behav Physiol, 2002-12) Jarvis, ED; Smith, VA; Wada, K; Rivas, MV; McElroy, M; Smulders, TV; Carninci, P; Hayashizaki, Y; Dietrich, F; Wu, X; McConnell, P; Yu, J; Wang, PP; Hartemink, AJ; Lin, S
    Biological systems by default involve complex components with complex relationships. To decipher how biological systems work, we assume that one needs to integrate information over multiple levels of complexity. The songbird vocal communication system is ideal for such integration due to many years of ethological investigation and a discreet dedicated brain network. Here we announce the beginnings of a songbird brain integrative project that involves high-throughput, molecular, anatomical, electrophysiological and behavioral levels of analysis. We first formed a rationale for inclusion of specific biological levels of analysis, then developed high-throughput molecular technologies on songbird brains, developed technologies for combined analysis of electrophysiological activity and gene regulation in awake behaving animals, and developed bioinformatic tools that predict causal interactions within and between biological levels of organization. This integrative brain project is fitting for the interdisciplinary approaches taken in the current songbird issue of the Journal of Comparative Physiology A and is expected to be conducive to deciphering how brains generate and perceive complex behaviors.
  • Thumbnail Image
    ItemOpen Access
    A neural network-based method for spectral distortion correction in photon counting x-ray CT.
    (Physics in medicine and biology, 2016-08) Touch, Mengheng; Clark, Darin P; Barber, William; Badea, Cristian T
    Spectral CT using a photon counting x-ray detector (PCXD) shows great potential for measuring material composition based on energy dependent x-ray attenuation. Spectral CT is especially suited for imaging with K-edge contrast agents to address the otherwise limited contrast in soft tissues. We have developed a micro-CT system based on a PCXD. This system enables both 4 energy bins acquisition, as well as full-spectrum mode in which the energy thresholds of the PCXD are swept to sample the full energy spectrum for each detector element and projection angle. Measurements provided by the PCXD, however, are distorted due to undesirable physical effects in the detector and can be very noisy due to photon starvation in narrow energy bins. To address spectral distortions, we propose and demonstrate a novel artificial neural network (ANN)-based spectral distortion correction mechanism, which learns to undo the distortion in spectral CT, resulting in improved material decomposition accuracy. To address noise, post-reconstruction denoising based on bilateral filtration, which jointly enforces intensity gradient sparsity between spectral samples, is used to further improve the robustness of ANN training and material decomposition accuracy. Our ANN-based distortion correction method is calibrated using 3D-printed phantoms and a model of our spectral CT system. To enable realistic simulations and validation of our method, we first modeled the spectral distortions using experimental data acquired from (109)Cd and (133)Ba radioactive sources measured with our PCXD. Next, we trained an ANN to learn the relationship between the distorted spectral CT projections and the ideal, distortion-free projections in a calibration step. This required knowledge of the ground truth, distortion-free spectral CT projections, which were obtained by simulating a spectral CT scan of the digital version of a 3D-printed phantom. Once the training was completed, the trained ANN was used to perform distortion correction on any subsequent scans of the same system with the same parameters. We used joint bilateral filtration to perform noise reduction by jointly enforcing intensity gradient sparsity between the reconstructed images for each energy bin. Following reconstruction and denoising, the CT data was spectrally decomposed using the photoelectric effect, Compton scattering, and a K-edge material (i.e. iodine). The ANN-based distortion correction approach was tested using both simulations and experimental data acquired in phantoms and a mouse with our PCXD-based micro-CT system for 4 bins and full-spectrum acquisition modes. The iodine detectability and decomposition accuracy were assessed using the contrast-to-noise ratio and relative error in iodine concentration estimation metrics in images with and without distortion correction. In simulation, the material decomposition accuracy in the reconstructed data was vastly improved following distortion correction and denoising, with 50% and 20% reductions in material concentration measurement error in full-spectrum and 4 energy bins cases, respectively. Overall, experimental data confirms that full-spectrum mode provides superior results to 4-energy mode when the distortion corrections are applied. The material decomposition accuracy in the reconstructed data was vastly improved following distortion correction and denoising, with as much as a 41% reduction in material concentration measurement error for full-spectrum mode, while also bringing the iodine detectability to 4-6 mg ml(-1). Distortion correction also improved the 4 bins mode data, but to a lesser extent. The results demonstrate the experimental feasibility and potential advantages of ANN-based distortion correction and joint bilateral filtration-based denoising for accurate K-edge imaging with a PCXD. Given the computational efficiency with which the ANN can be applied to projection data, the proposed scheme can be readily integrated into existing CT reconstruction pipelines.
  • Thumbnail Image
    ItemOpen Access
    A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.
    (PLoS Comput Biol, 2015-08) Alemi, Alireza; Baldassi, Carlo; Brunel, Nicolas; Zecchina, Riccardo
    Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the number of stored patterns.
  • Thumbnail Image
    ItemOpen Access
    Fibroblast growth factor23 is associated with axonal integrity and neural network architecture in the human frontal lobes.
    (PloS one, 2018-01) Marebwa, Barbara K; Adams, Robert J; Magwood, Gayenell S; Kindy, Mark; Wilmskoetter, Janina; Wolf, Myles; Bonilha, Leonardo
    Elevated levels of FGF23 in individuals with chronic kidney disease (CKD) are associated with adverse health outcomes, such as increased mortality, large vessel disease, and reduced white matter volume, cardiovascular and cerebrovascular events. Apart from the well-known link between cardiovascular (CV) risk factors, especially diabetes and hypertension, and cerebrovascular damage, elevated FGF23 is also postulated to be associated with cerebrovascular damage independently of CKD. Elevated FGF23 predisposes to vascular calcification and is associated with vascular stiffness and endothelial dysfunction in the general population with normal renal function. These factors may lead to microangiopathic changes in the brain, cumulative ischemia, and eventually to the loss of white matter fibers. The relationship between FGF23 and brain integrity in individuals without CKD has hitherto not been investigated. In this study, we aimed to determine the association between FGF23, and white matter integrity in a cohort of 50 participants with varying degrees of CV risk burden, using high resolution structural human brain connectomes constructed from MRI diffusion images. We observed that increased FGF23 was associated with axonal loss in the frontal lobe, leading to a fragmentation of white matter network organization. This study provides the first description of the relationship between elevated levels of FGF23, white matter integrity, and brain health. We suggest a synergistic interaction of CV risk factors and FGF23 as a potentially novel determinant of brain health.
  • Thumbnail Image
    ItemOpen Access
    Neural network analysis identifies scaffold properties necessary for in vitro chondrogenesis in elastin-like polypeptide biopolymer scaffolds.
    (Tissue Eng Part A, 2010-01) Nettles, Dana L; Haider, Mansoor A; Chilkoti, Ashutosh; Setton, Lori A
    The successful design of biomaterial scaffolds for articular cartilage tissue engineering requires an understanding of the impact of combinations of material formulation parameters on diverse and competing functional outcomes of biomaterial performance. This study sought to explore the use of a type of unsupervised artificial network, a self-organizing map, to identify relationships between scaffold formulation parameters (crosslink density, molecular weight, and concentration) and 11 such outcomes (including mechanical properties, matrix accumulation, metabolite usage and production, and histological appearance) for scaffolds formed from crosslinked elastin-like polypeptide (ELP) hydrogels. The artificial neural network recognized patterns in functional outcomes and provided a set of relationships between ELP formulation parameters and measured outcomes. Mapping resulted in the best mean separation amongst neurons for mechanical properties and pointed to crosslink density as the strongest predictor of most outcomes, followed by ELP concentration. The map also grouped formulations together that simultaneously resulted in the highest values for matrix production, greatest changes in metabolite consumption or production, and highest histological scores, indicating that the network was able to recognize patterns amongst diverse measurement outcomes. These results demonstrated the utility of artificial neural network tools for recognizing relationships in systems with competing parameters, toward the goal of optimizing and accelerating the design of biomaterial scaffolds for articular cartilage tissue engineering.
  • Thumbnail Image
    ItemOpen Access
    Optimal properties of analog perceptrons with excitatory weights.
    (PLoS Comput Biol, 2013) Clopath, Claudia; Brunel, Nicolas
    The cerebellum is a brain structure which has been traditionally devoted to supervised learning. According to this theory, plasticity at the Parallel Fiber (PF) to Purkinje Cell (PC) synapses is guided by the Climbing fibers (CF), which encode an 'error signal'. Purkinje cells have thus been modeled as perceptrons, learning input/output binary associations. At maximal capacity, a perceptron with excitatory weights expresses a large fraction of zero-weight synapses, in agreement with experimental findings. However, numerous experiments indicate that the firing rate of Purkinje cells varies in an analog, not binary, manner. In this paper, we study the perceptron with analog inputs and outputs. We show that the optimal input has a sparse binary distribution, in good agreement with the burst firing of the Granule cells. In addition, we show that the weight distribution consists of a large fraction of silent synapses, as in previously studied binary perceptron models, and as seen experimentally.