644 research outputs found
Author response: Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
No full textMemory-augmented neural networks : enhancing biological plausibility and task-learnability
No full textLAUREA MAGISTRALEOttenute dall'unione di reti neurali con un sistema di memoria, le Memory-Augmented Neural Networks (MANNs) rappresentano una nuova frontiera dell'intelligenza artificiale, grazie alla combinazione della crescente capacità di apprendimento delle rete neurali artificiali e della possibilità di salvare e recuperare importanti informazioni dalla memoria. Essendo un argomento estremamente attuale sia nel campo del machine learning che della neuroscienza cognitiva, le MANNs sono state sviluppate in direzioni opposte, raggiungendo diversi traguardi in termini di performance di apprendimento e di plausibilità biologica.
Il presente lavoro di tesi esplora le capacità delle MANNs comparando le performance di diversi modelli su una serie di task cognitivi con una crescente richiesta di capacità di memorizzazione, per poi identificare vantaggi e criticità e proporre alternative ai modelli originali. Nello specifico, lo studio si concentra su due modelli a memoria interna con forti basi biologiche (AuGMEnT e HER) e su quella che ad oggi è considerata la miglior rete neurale a memoria esterna, il DNC.
In particolare, i risultati comparativi portano alla luce una difficoltà del modello AuGMEnT in merito all'immagazzinamento di sequenze di stimoli in maniera stabile, il che non permette la corretta risoluzione di task affetti dal cosiddetto temporal credit assignment problem, come il task 12AX; al contrario, il modello DNC conferma le sue eccellenti prestazioni di apprendimento in tutti i casi testati, ma è penalizzato da una bassa credibilità dal punto di vista neuro-biologico. Pertanto, sono state proposte tre varianti del modello AuGMEnT per superare le sue debolezze di apprendimento: leaky-AuGMEnT, deep AuGMEnT e hierarchical AuGMEnT. Inoltre, lo schema di scrittura/lettura di DNC è stato ridotto ad un approccio puramente content-based (R-DNC) - più biologicamente verosimile - e successivamente integrato con il modulo LRUA per recuperare la capacità di apprendimento one-shot nel caso di task di classificazione come Omniglot.Result of the union of Artificial Neural Networks with memory, Memory-Augmented Neural Networks (MANNs) represent a new frontier in artificial intelligence, thanks to the combination of the increasing learning capacity of neural networks with the possibility to store and retrieve relevant information from memory. Being a trend topic in both the machine learning community and in cognitive neuroscience, the MANNs have been developed independently in opposite directions with various achievements in terms of learning performance and biological plausibility.
In the present work, we have explored the capacities of MANNs by comparing the performance of specific models on a sequence of cognitive tasks with an increasing demand of memory dynamics, in such a way to identify advantages and limitations and propose new solutions. Specifically, the study involves two neurally faithful models with internal memory (AuGMEnT and HER) and the current top-performing MANN with external memory, the DNC.
In particular, the comparative results showed that AuGMEnT model suffers from memory interference that hampers correct learning of tasks affected by temporal credit assignemnt problem, like 12AX task; on the other side, the DNC network confirmed its excellent performance, but it is penalized by low biological foundations. Afterwards, we proposed three variants of AuGMEnT to overcome its learning limitations: leaky-AuGMEnT, deep AuGMEnT and hierarchical AuGMEnT. Morevoer, the addressing scheme of the DNC model has been simplified to pure content-based approach (R-DNC) and coupled with LRUA access module to restore one-shot learning on classification tasks, like the Omniglot task
Dentigerous Cyst
No full textDentigerous Cyst
Dental School Radiology Presentation : Dentigerous Cyst
Author : Tadinada, Aditya
Medical Subject : Dentigerous Cyst, Odontogenic Cysts
Clinical Presentation Description : Radiolucency arising from the CEJ of an unerupted tooth
Location of Abnormality : Posterior Mandible
Radiological Features : Radiolucency arising from the CEJ of an unerupted tooth
DDx Description : Dentigerous cyst, odontogenic keratocyst, ameloblastoma
Type of Image : Panoramic Radiograph
Digital Publisher : UCONN Health Center : Kilham, Jessica
Format : jpg
Date : 201
Design, modeling and real-time monitoring of continuous powder mixing processes
No full textContinuous processing is an advantageous alternative for the current methods used in the pharmaceutical manufacturing. Important advantages that it offers include smaller equipment footprint, reduced efforts in the scale-up work, and the potential to utilize already continuous processes to make the entire manufacturing more efficient. In the current pharmaceutical manufacturing environment, powder mixing process is carried out in the batch mode. The necessary methods and guidelines to design an equivalent continuous process are not well established. The work presented in this dissertation focuses on the characterization, design and optimization of a continuous powder mixing process for pharmaceutical powders. A systematic study was performed of the effects of process and design variables, and material properties involved in the continuous powder mixing process. The bulk powder flow behavior was characterized using the residence time distribution (RTD) measurement approach. Impeller speed, material bulk density and impeller design greatly influenced the mean residence time. With increasing impeller speed, mechanical fluidization was observed, which significantly affected axial dispersion coefficients. Intermediate rotation rates exerted maximum strain on the material, which leads to maximum homogenization. The strain measurements correlated well with the properties of tablets including content uniformity and tablet hardness. Mixing performance was largely dominated by the material properties of the mixture, and the blend uniformity measurement was affected by the sample size analyzed. An experimental protocol was developed to measure the blend uniformity in the in-line mode, and a methodology was further built to quantitatively relate the in-line NIR measurements with the off-line wet chemistry measurements. Considering the shear limitations of the continuous bladed mixer, alternative blending strategies, suitable for blending of cohesive materials were also demonstrated. A combination of a high-shear mixing followed by a low-shear mixing process provided the optimal mixing performance. The predictive understanding of the continuous powder mixing process developed in this dissertation can assist towards the design and development of a fully controlled continuous manufacturing process.Ph. D.Includes bibliographical referencesIncludes vitaby Aditya U. Vanaras
adityagilra/BeliefStateRL
No full textThis is the code and experimental data to simulate and fit the Basic RL and Belief State RL models from the bioRxiv preprint Cole, et al., Prediction-error signals in anterior cingulate cortex drive task-switching, 2022, version 2
Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
No full textThe brain needs to predict how the body reacts to motor commands, but how a network of spiking neurons can learn non-linear body dynamics using local, online and stable learning rules is unclear. Here, we present a supervised learning scheme for the feedforward and recurrent connections in a network of heterogeneous spiking neurons. The error in the output is fed back through fixed random connections with a negative gain, causing the network to follow the desired dynamics. The rule for Feedback-based Online Local Learning Of Weights (FOLLOW) is local in the sense that weight changes depend on the presynaptic activity and the error signal projected onto the postsynaptic neuron. We provide examples of learning linear, non-linear and chaotic dynamics, as well as the dynamics of a two-link arm. Under reasonable approximations, we show, using the Lyapunov method, that FOLLOW learning is uniformly stable, with the error going to zero asymptotically.LC
Crystal Dynamics and Anharmonic Properties of Bi-Pb-Tl Alloys
No full textTitle: Crystal Dynamics and Anharmonic Properties of Bi-Pb-Tl Alloys, Author: Aditya P. Roy, Location: ThodeThe crystal dynamics and anharmonic properties have
been investigated in disordered alloys of Bi-Pb-Tl using slow
neutron spectrometry. Damping of phonons caused by phonon-phonon
interaction and the effect of the force constant
disorder on the lifetime of the phonons have been studied in
the alloys. Measurements of the coefficients of thermal
expansion are reported. An experimental method of determining
the lattice frequency spectra by coherent inelastic scattering
of neutrons from polycrystalline materials is described.ThesisDoctor of Philosophy (PhD
On the two-potential constitutive modelling of rubber viscoelastic materials
No full textU of I Only Restriction Lifted for Item 93166 on 2018-07-08T09:15:36Z."This work lays out the specialization of the two-potential constitutive framework --- also known as the ""generalized standard materials'' framework --- to rubber viscoelasticity. Inter alia, it is shown that a number of popular rubber viscoelasticity formulations, introduced over the years following different approaches, are special cases of this framework. As a first application of practical relevance, the framework is utilized to put forth a new objective and thermodynamically consistent rubber viscoelastic model for incompressible isotropic elastomers. The model accounts for the non-Gaussian elasticity of elastomers, as well as for the deformation-enhanced shear thinning of their viscous dissipation governed by reptation dynamics. The descriptive and predictive capabilities of the model are illustrated via comparisons with experimental data available from the literature for two commercially significant elastomers."Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2018-05-01The student, Aditya Kumar, accepted the attached license on 2016-04-21 at 16:42.The student, Aditya Kumar, submitted this Thesis for approval on 2016-04-21 at 17:40.This Thesis was approved for publication on 2016-04-25 at 13:53.DSpace SAF Submission Ingestion Package generated from Vireo submission #9421 on 2016-07-07 at 13:50:34Made available in DSpace on 2016-07-07T20:27:55Z (GMT). No. of bitstreams: 2
KUMAR-THESIS-2016.pdf: 837141 bytes, checksum: 4cd6a13625dabb966b6db0afa249edcc (MD5)
LICENSE.txt: 4209 bytes, checksum: 0e09e0cd09aa5811ed8246d9f3eb6e6d (MD5)
Previous issue date: 2016-04-25Embargo set by: Seth Robbins for item 93166
Lift date: 2018-07-07T20:28:14Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD systemEmbargo set by: Seth Robbins for item 93166
Lift date: 2018-07-07T20:35:34Z
Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD syste
Stitches: Blending landscape fabric through the golden threads of spatial identity in San Riku coastline, Otsuchi, Iwate, Japan
No full textDisaster prevention and coastal protection of Otsuchi have affected the livelihood and the daily pattern of lifestyle of the regular Otsuchian. This work represents the alternative to a typical top down prefectural level demand for a line based infrastructural solution to disaster prevention and creates the required importance of livelihood, culture and identity of a place over the protection structure. While in the design of such critical areas it is important to place protection of the citizens at a high level, it is also a necessity to understand the situation of each city as different from each other. In this way, the genius loci of a place is founded. Along the San Riku coastline where the tsunami and earthquake hit the hardest due to the landscape features and the proximity to the epicenter the government has set a list of top down governed structures that have impacted the urban fabric of the city, This document looks at one of these towns “Otsuchi” and how alternate solutions based on the historical and landscape features of the district can help create landscapes of livelihood for the citizens. Otsuchi among many other Japanese cities faces the issue of a shrinking population due to a lack of economy, a lack of education in the rural areas and a lack of opportunities. The design document also looks at how Identity crisis in a Rias coastline/ Aditya Athreya Rao/ TU Delft 1 landscape can create a set of cyclical opportunities for the people to develop their town responsibly and sustain-ably as they see fit. Landscape design seeks to provide opportunity to the stakeholders to further create, it provides the platform for this creation and the thesis looks at ideas and solutions on ways this can be done. Keywords: Landscape Infrastructure, Identity, Contextual Design Genius Loci, Landscape Design, New landscapesFlowscapesArchitecture, Urbanism and Building Sciences | Landscape Architectur
- …
