Fast Adaptation Research Articles

A bio-inspired reinforcement learning model that accounts for fast adaptation after punishment

Humans and animals can quickly learn a new strategy when a previously-rewarding strategy is punished. It is difficult to model this with reinforcement learning methods, because they tend to perseverate on previously-learned strategies − a hallmark of impaired response to punishment. Past work has addressed this by augmenting conventional reinforcement learning equations with ad hoc parameters or parallel learning systems. This produces reinforcement learning models that account for reversal learning, but are more abstract, complex, and somewhat detached from neural substrates. Here we use a different approach: we generalize a recently-discovered neuron-level learning rule, on the assumption that it captures a basic principle of learning that may occur at the whole-brain-level. Surprisingly, this gives a new reinforcement learning rule that accounts for adaptation and lose-shift behavior, and uses only the same parameters as conventional reinforcement learning equations. In the new rule, the normal reward prediction errors that drive reinforcement learning are scaled by the likelihood the agent assigns to the action that triggered a reward or punishment. The new rule demonstrates quick adaptation in card sorting and variable Iowa gambling tasks, and also exhibits a human-like paradox-of-choice effect. It will be useful for experimental researchers modeling learning and behavior.

Comprehensive Assessment of Initial Adaptation of ESBL Positive ST131 Escherichia coli to Carbapenem Exposure.

It remains unclear how high-risk Escherichia coli lineages, like sequence type (ST) 131, initially adapt to carbapenem exposure in their progression to becoming carbapenem resistant. Carbapenem mutation frequency was measured in multiple subclades of extended-spectrum β-lactamase (ESBL) positive ST131 clinical isolates using a fluctuation assay followed by whole genome sequencing (WGS) characterization. Genomic, transcriptomic, and porin analyses of ST131 C2/ H 30Rx isolate, MB1860, under prolonged, increasing carbapenem exposure was performed using two distinct experimental evolutionary platforms to measure fast vs. slow adaptation. All thirteen ESBL positive ST131 strains selected from a diverse (n=184) ST131 bacteremia cohort had detectable ertapenem (ETP) mutational frequencies with a statistically positive correlation between initial ESBL gene copy number and mutation frequency (r = 0.87, P -value <1e-5). WGS analysis of mutants showed initial response to ETP exposure resulted in significant increases in ESBL gene copy numbers or mutations in outer membrane porin (Omp) encoding genes in the absence of ESBL gene amplification with subclade specific associations. In both experimental evolutionary platforms, MB1860 responded to initial ETP exposure by increasing bla CTX-M-15 copy numbers via modular, insertion sequence 26 (IS 26 ) mediated pseudocompound transposons (PCTns). Transposase activity driven by PCTn upregulation was a conserved expression signal in both experimental evolutionary platforms. Stable mutations in Omp encoding genes were detected only after prolonged increasing carbapenem exposure consistent with clinical observations. ESBL gene amplification is a conserved response to initial carbapenem exposure, especially within the high-risk ST131 C2/ H 30Rx subclade. Targeting such amplification could assist with mitigating carbapenem resistance development.

Systematic Improvement of a Bolus Calculator That Is on the Market: A User-Centric Approach.

State-of-the-art diabetes self-management includes the usage of (software) tools, such as Bolus Calculators, to support patients with their therapeutic decisions. The development of such medical devices comes with strict obligations to ensure the safety and performance for the user; however, it is also necessary to continue to evaluate such aspects after the products are introduced into the market. In addition, such aspects cannot always be sufficiently validated by clinical trials; they need real-world evaluation to systematically improve such tools while they are on the market. The approach described here uses innovative ways of generating user-centric evidence to improve the bolus calculator, including (1) human factor engineering, (2) analysis of glycemic real-world data, (3) patient-reported outcomes, and (4) machine-generated behavioral measurements. The combination of the diverse techniques to optimize the bolus calculator triggered changes in the user experience: a significant reduction in hypoglycemic events, -0.52% (±0.05), P < .01, n=3480, an increased diabetes treatment satisfaction (Diabetes Treatment Satisfaction Questionnaire [DTSQ] +9.90, P < .01, n=217), as well as an increased acceptance rate of bolus calculations, +15.73 (±0.89), P < .01, n=3436, were observed. Altogether, human factor engineering and different forms of real-world data support fast and direct adaptations and improvements in products used for diabetes therapy.

An information fusion-based meta transfer learning method for few-shot fault diagnosis under varying operating conditions

In recent years, meta-learning has gained increasing attention in the field of fault diagnosis due to its advantages of handling small samples and exhibiting fast adaptation across different diagnostic tasks. However, the scenario of sharply varying operating conditions and the heavy computation burden still limit the effective application of meta-learning in the field of transfer fault diagnosis. To address the above challenges, a few-shot meta transfer diagnosis method is proposed based on information fusion-based model agnostic meta-learning (IFMAML). Firstly, the information enhancement method based on sparse principal component analysis is introduced to enhance the domain invariant features and reduce data redundancy. Subsequently, the information fusion strategy of multiple sensor data is proposed to form the red, green, and blue (RGB) channel information of images, which can enrich the diversity of domain invariant features and mine the spatial information of multiple sensors. Then, the IFMAML, with its enhanced potential for diagnostic performance and computational efficiency, is developed to address the challenging few-shot cross-domain transfer diagnosis under varying operating conditions. Finally, two case studies for gearbox fault diagnostics considering sharply varying speed conditions and unknown health conditions have been conducted to demonstrate the effectiveness and superiority of the proposed method. Experimental results have indicated that the proposed IFMAML method can achieve superior diagnostic accuracy and can be quickly adapted to new transfer diagnosis scenarios under varying operating conditions, when compared with several mainstream meta-learning methods.

Exploring Electrocortical Signatures of Gait Adaptation: Differential Neural Dynamics in Slow and Fast Gait Adapters.

Individuals exhibit significant variability in their ability to adapt locomotor skills, with some adapting quickly and others more slowly. Differences in brain activity likely contribute to this variability, but direct neural evidence is lacking. We investigated individual differences in electrocortical activity that led to faster locomotor adaptation rates. We recorded high-density electroencephalography while young, neurotypical adults adapted their walking on a split-belt treadmill and grouped them based on how quickly they restored their gait symmetry. Results revealed unique spectral signatures within the posterior parietal, bilateral sensorimotor, and right visual cortices that differ between fast and slow adapters. Specifically, fast adapters exhibited lower alpha power in the posterior parietal and right visual cortices during early adaptation, associated with quicker attainment of steady-state step length symmetry. Decreased posterior parietal alpha may reflect enhanced spatial attention, sensory integration, and movement planning to facilitate faster locomotor adaptation. Conversely, slow adapters displayed greater alpha and beta power in the right visual cortex during late adaptation, suggesting potential differences in visuospatial processing. Additionally, fast adapters demonstrated reduced spectral power in the bilateral sensorimotor cortices compared with slow adapters, particularly in the theta band, which may suggest variations in perception of the split-belt perturbation. These findings suggest that alpha and beta oscillations in the posterior parietal and visual cortices and theta oscillations in the sensorimotor cortex are related to the rate of gait adaptation.

Neural Network Inspired Binder Enables Fast Li-Ion Transport and High Stress Adaptation for Si Anode.

Extensive investigations have proven the effectiveness of elastic binders in settling the challenge of structural damage posed by volume expansion of high-capacity anode used in nanoscale silicon. However, the sluggish ionic conductivity of polymer binder severely restricts the electrode reactions, making it unsuitable for practical applications. Inspired by the biological tissues with rapid neurotransmission and robust muscles, we propose a biomimetic binder that contains ionic conductive polymer (by polymerization reaction of poly(ethylene glycol) diglycidyl ether and polyethylenimine) and rigid polymer backbone (polyacrylic acid), which can effectively mitigate both Li-ion transport resistance and lithiation stress to stabilize the silicon nanoparticles during cycles. Consequently, the silicon anode with biomimetic binder achieves a rate capability of 1897 mAh g-1 at 8.0 A g-1 and capacity retention of 87% after 150 cycles under areal capacity upon 3.0 mAh cm-2. These results demonstrate the possibility of decoupling ionic conductivity from mechanical properties toward practical high-capacity anodes for energy-dense batteries.

Hepatic ketogenesis is not required for starvation adaptation in mice

ObjectiveIn response to bacterial inflammation, anorexia of acute illness is protective and is associated with the induction of fasting metabolic programs such as ketogenesis. Forced feeding during the anorectic period induced by bacterial inflammation is associated with suppressed ketogenesis and increased mortality. As ketogenesis is considered essential in fasting adaptation, we sought to determine the role of ketogenesis in illness-induced anorexia. MethodsA mouse model of inducible hepatic specific deletion of the rate limiting enzyme for ketogenesis (HMG-CoA synthase 2, Hmgcs2) was used to investigate the role of ketogenesis in endotoxemia, a model of bacterial inflammation, and in prolonged starvation. ResultsMice deficient of hepatic Hmgcs2 failed to develop ketosis during endotoxemia and during prolonged fasting. Surprisingly, hepatic HMGCS2 deficiency and the lack of ketosis did not affect survival, glycemia, or body temperature in response to endotoxemia. Mice with hepatic ketogenic deficiency also did not exhibit any defects in starvation adaptation and were able to maintain blood glucose, body temperature, and lean mass compared to littermate wild-type controls. Mice with hepatic HMGCS2 deficiency exhibited higher levels of plasma acetate levels in response to fasting. ConclusionsCirculating hepatic-derived ketones do not provide protection against endotoxemia, suggesting that alternative mechanisms drive the increased mortality from forced feeding during illness-induced anorexia. Hepatic ketones are also dispensable for surviving prolonged starvation in the absence of inflammation. Our study challenges the notion that hepatic ketogenesis is required to maintain blood glucose and preserve lean mass during starvation, raising the possibility of extrahepatic ketogenesis and use of alternative fuels as potential means of metabolic compensation.

The partial adaptation strategy for online-adaptive proton therapy: A proof of concept study in head and neck cancer patients.

The accuracy of intensity-modulated proton therapy (IMPT) is greatly affected by anatomy variations that might occur during the treatment course. Online plan adaptations have been proposed as a solution to intervene promptly during a treatment session once the anatomy changes are detected. The implementation of online-adaptive proton therapy (OAPT) is still hindered by time-consuming tasks in the workflow. The study introduces the novel concept of partial adaptation and aims at investigating its feasibility as a potential solution to parallelize tasks during an OAPT workflow for saving valuable in-room time. The proof-of-principle simulation study includes datasets from six head and neck cancer (HNC) patients, each consisting of one planning CT (pCT) and three contoured control CTs (cCTs). Robust 3-field normo-fractionated initial IMPT plans were generated on the pCTs with a standardized field configuration, delivering 66 Gy and 54Gy to the high-risk and low-risk clinical target volume (CTVHigh and CTVLow), respectively.For each cCT, a dose-mimicking-based partial adaptation was applied: two fields were adapted on the current anatomy taking into account the background dose of the first non-adapted field supposedly delivered in the meantime. Fraction doses on the cCTs resulting from partially adapted plans with different first (non-adapted) field assignments were compared against those from non-adapted and fully adapted plans regarding target coverage and organs at risk (OARs) sparing. The robustness of partially adapted plans was also evaluated. Partially adapted plans showed comparable results to fully adapted plans and were superior to non-adapted plans for both target coverage and OAR sparing. Target coverage degradation in the non-adapted plans (median D98%: 95.9% and 97.5% for CTVLow and CTVHigh, respectively) was recovered by both partial (98.0% and 98.5%) and full adaptation (98.2% and 98.7%) in comparison to the initial plans (98.7% and 98.8%). The initial hotspot dose for the CTVHigh (median D2%: 101.8%) increased in the non-adapted plans (102.9%) and was recovered by the adaptive strategies (partial: 102.5%, full: 101.9%). The near-maximum dose (D0.01cc) to brainstem and spinal cord was within clinical constraints for all investigated dose distributions, but clearly increased for no adaptation and improved in the (both partially and fully) adapted plans with respect to the non-adapted ones. The parotids' median doses (D50) were mainly patient-specific depending on the proximity to the target region, but anyway lower for the partially and fully adapted plans compared to the non-adapted ones. OAR sparing was furthermore improved for the partially adapted plans in comparison to full adaptation. Robustness of the target dose metrics was preserved in all evaluated scenarios. For OAPT of HNC patients, partial adaptation is able to generate plans of superior conformity to non-adapted plans and of comparable conformity as fully adapted plans, while having the potential to speed up the online-adaptive workflows. Thus, partial adaptation represents an intermediate approach until fast online adaptation workflows become available. Furthermore, it can be applied in workflows where online treatment verification stops the delivery and triggers an online adaptation for the remaining fraction.

Potassium-mediated bacterial chemotactic response.

Bacteria in biofilms secrete potassium ions to attract free swimming cells. However, the basis of chemotaxis to potassium remains poorly understood. Here, using a microfluidic device, we found that Escherichia coli can rapidly accumulate in regions of high potassium concentration on the order of millimoles. Using a bead assay, we measured the dynamic response of individual flagellar motors to stepwise changes in potassium concentration, finding that the response resulted from the chemotaxis signaling pathway. To characterize the chemotactic response to potassium, we measured the dose-response curve and adaptation kinetics via an Förster resonance energy transfer (FRET) assay, finding that the chemotaxis pathway exhibited a sensitive response and fast adaptation to potassium. We further found that the two major chemoreceptors Tar and Tsr respond differently to potassium. Tar receptors exhibit a biphasic response, whereas Tsr receptors respond to potassium as an attractant. These different responses were consistent with the responses of the two receptors to intracellular pH changes. The sensitive response and fast adaptation allow bacteria to sense and localize small changes in potassium concentration. The differential responses of Tar and Tsr receptors to potassium suggest that cells at different growth stages respond differently to potassium and may have different requirements for potassium.

Potassium-mediated bacterial chemotactic response

Bacteria in biofilms secrete potassium ions to attract free swimming cells. However, the basis of chemotaxis to potassium remains poorly understood. Here, using a microfluidic device, we found that Escherichia coli can rapidly accumulate in regions of high potassium concentration on the order of millimoles. Using a bead assay, we measured the dynamic response of individual flagellar motors to stepwise changes in potassium concentration, finding that the response resulted from the chemotaxis signaling pathway. To characterize the chemotactic response to potassium, we measured the dose–response curve and adaptation kinetics via an Förster resonance energy transfer (FRET) assay, finding that the chemotaxis pathway exhibited a sensitive response and fast adaptation to potassium. We further found that the two major chemoreceptors Tar and Tsr respond differently to potassium. Tar receptors exhibit a biphasic response, whereas Tsr receptors respond to potassium as an attractant. These different responses were consistent with the responses of the two receptors to intracellular pH changes. The sensitive response and fast adaptation allow bacteria to sense and localize small changes in potassium concentration. The differential responses of Tar and Tsr receptors to potassium suggest that cells at different growth stages respond differently to potassium and may have different requirements for potassium.

Memristor-based adaptive neuromorphic perception in unstructured environments

Efficient operation of control systems in robotics or autonomous driving targeting real-world navigation scenarios requires perception methods that allow them to understand and adapt to unstructured environments with good accuracy, adaptation, and generality, similar to humans. To address this need, we present a memristor-based differential neuromorphic computing, perceptual signal processing, and online adaptation method providing neuromorphic style adaptation to external sensory stimuli. The adaptation ability and generality of this method are confirmed in two application scenarios: object grasping and autonomous driving. In the former, a robot hand realizes safe and stable grasping through fast ( ~ 1 ms) adaptation based on the tactile object features with a single memristor. In the latter, decision-making information of 10 unstructured environments in autonomous driving is extracted with an accuracy of 94% with a 40×25 memristor array. By mimicking human low-level perception mechanisms, the electronic neuromorphic circuit-based method achieves real-time adaptation and high-level reactions to unstructured environments.

Integrative ATAC-seq and RNA-seq Analysis of the Longissimus Dorsi Muscle of Gannan Yak and Jeryak.

Jeryak is the F1 generation of the cross between Gannan yak and Jersey cattle, which has the advantages of fast growth and high adaptability. The growth and development of skeletal muscle is closely linked to meat production and the quality of meat. However, the molecular regulatory mechanisms of muscle growth differences between Gannan yak and Jeryak analyzed from the perspective of chromatin opening have not been reported. In this study, ATAC-seq was used to analyze the difference of chromatin openness in longissimus muscle of Gannan yak and Jeryak. It was found that chromatin accessibility was more enriched in Jeryak compared to Gannan yak, especially in the range of the transcription start site (TSS) ± 2 kb. GO and KEGG enrichment analysis indicate that differential peak-associated genes are involved in the negative regulation of muscle adaptation and the Hippo signaling pathway. Integration analysis of ATAC-seq and RNA-seq revealed overlapping genes were significantly enriched during skeletal muscle cell differentiation and muscle organ morphogenesis. At the same time, we screened FOXO1, ZBED6, CRY2 and CFL2 for possible involvement in skeletal muscle development, constructed a genes and transcription factors network map, and found that some transcription factors (TFs), including YY1, KLF4, KLF5 and Bach1, were involved in skeletal muscle development. Overall, we have gained a comprehensive understanding of the key factors that impact skeletal muscle development in various breeds of cattle, providing new insights for future analysis of the molecular regulatory mechanisms involved in muscle growth and development.

Integration of MoS2 Memtransistor Devices and Analogue Circuits for Sensor Fusion in Autonomous Vehicle Target Localization.

In contemporary autonomous driving systems relying on sensor fusion, traditional digital processors encounter challenges associated with analogue-to-digital conversion and iterative vector-matrix operations, which are encumbered by limitations in terms of response time and energy consumption. In this study, we present an analogue Kalman filter circuit based on molybdenum disulfide (MoS2) memtransistor, designed to accelerate sensor fusion for precise localization in autonomous vehicle applications. The nonvolatile memory characteristics of the memtransistor allow for the storage of a fixed Kalman gain, which eliminates the data convergence and thus accelerates the processing speeds. Additionally, the modulation of multiple conductance states by the gate terminal enables fast adaptability to diverse autonomous driving scenarios by tuning multiple Kalman filter gains. Our proposed analogue Kalman filter circuit accurately estimates the position coordinates of target vehicles by fusing sensor data from light detection and ranging (LiDAR), millimeter-wave radar (Radar), and camera, and it successfully solves real-word problems in a signal-free crossroad intersection. Notably, our system achieves a 1000-fold improvement in energy efficiency compared to that of digital circuits. This work underscores the viability of a memtransistor for achieving fast, energy-efficient real-time sensing, and continuous signal processing in advanced sensor fusion technology.

Optimizing modular equipment in the design of multi-product reconfigurable production lines

This work addresses the problem of the design and balancing of a modular multi-product line in a reconfigurable environment. The study emphasizes the importance of modularity in the reconfigurable manufacturing systems (RMS), which allows fast, efficient, and cost-effective adaptation to changes by rearranging, moving, or removing modules. The line consists of a fixed number of modular machines arranged linearly and connected by a material handling system. Each machine has a limited number of slots for modules. The line can handle several product types per batch, and each batch requires a specific line configuration to be produced. The objective consists in identifying the minimum number of modules needed and their arrangement in different configurations to produce each product type. To solve this problem, a compact integer linear programming (ILP) formulation is initially investigated. Then an ILP reformulation, based on a decomposition approach, as well as a heuristic that uses this ILP reformulation are developed. The results demonstrate the effectiveness of the proposed methods.

DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition With Limited Annotations

DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition With Limited Annotations

Residual OXPHOS is required to drive primary and metastatic lung tumours in an orthotopic breast cancer model.

Fast adaptation of glycolytic and mitochondrial energy pathways to changes in the tumour microenvironment is a hallmark of cancer. Purely glycolytic ρ0 tumour cells do not form primary tumours unless they acquire healthy mitochondria from their micro-environment. Here we explored the effects of severely compromised respiration on the metastatic capability of 4T1 mouse breast cancer cells. 4T1 cell lines with different levels of respiratory capacity were generated; the Seahorse extracellular flux analyser was used to evaluate oxygen consumption rates, fluorescent confocal microscopy to assess the number of SYBR gold-stained mitochondrial DNA nucleoids, and the presence of the ATP5B protein in the cytoplasm and fluorescent in situ nuclear hybridization was used to establish ploidy. MinION nanopore RNA sequence analysis was used to compare mitochondrial DNA transcription between cell lines. Orthotopic injection was used to determine the ability of cells to metastasize to the lungs of female Balb/c mice. OXPHOS-deficient ATP5B-KO3.1 cells did not generate primary tumours. Severely OXPHOS compromised ρ0D5 cells generated both primary tumours and lung metastases. Cells generated from lung metastasis of both OXPHOS-competent and OXPHOS-compromised cells formed primary tumours but no metastases when re-injected into mice. OXPHOS-compromised cells significantly increased their mtDNA content, but this did not result in increased OXPHOS capacity, which was not due to decreased mtDNA transcription. Gene set enrichment analysis suggests that certain cells derived from lung metastases downregulate their epithelial-to-mesenchymal related pathways. In summary, OXPHOS is required for tumorigenesis in this orthotopic mouse breast cancer model but even very low levels of OXPHOS are sufficient to generate both primary tumours and lung metastases.

Concept of a Peripheral-Free Electrified Monorail System (PEMS) for Flexible Material Handling in Intralogistics

Concept of a Peripheral-Free Electrified Monorail System (PEMS) for Flexible Material Handling in Intralogistics

Fast Track Adaptation of Oncolytic Coxsackie B3 Virus to Resistant Colorectal Cancer Cells - a Method to Personalize Virotherapy

BackgroundThe efficacy of oncolytic viruses (OV) in cancer treatment depends on their ability to successfully infect and destroy tumor cells. However, patients’ tumors vary, and in the case of individual insensitivity to an OV, therapeutic efficacy is limited. Here, we present a protocol for rapid generation of tumor cell-specific adapted oncolytic coxsackievirus B3 (CVB3) with enhanced oncolytic potential and a satisfactory safety profile. This is achieved by combining directed viral evolution (DVE) with genetic modification of the viral genome and the use of a microRNA-dependent regulatory tool.MethodsThe oncolytic CVB3 variant PD-H was adapted to the refractory colorectal carcinoma cell line Colo320 through serial passaging. XTT assays and virus plaque assays were used to determine virus cytotoxicity and virus replication in vitro. Recombinant PD-H variants were generated through virus mutagenesis. Apoptosis was detected by Western blots, Caspase 3/7 assays, and DAPI staining. The therapeutic efficacy and safety of the adapted recombinant OV PD-SK-375TS were assessed in vivo using a subcutaneous Colo320 xenograft mouse model.ResultsPD-H was adapted to the colorectal cancer cell line Colo320 within 10 passages. Sequencing of passage 10 virus P-10 revealed a heterogenous virus population with five nucleotide mutations resulting in amino acid substitutions. The genotypically homogeneous OV PD-SK was generated by inserting the five detected mutations of P-10 into the genome of PD-H. PD-SK showed significantly stronger replication and cytotoxicity than PD-H in Colo320 cells, but not in other colorectal carcinoma cell lines. Increase of apoptosis induction was detected as key mechanisms of Colo320 cell-specific adaptation of PD-SK. For in vivo safety PD-SK was engineered with target sites of the miR-375 (miR-375TS) to exclude virus replication in normal tissues. PD-SK-375TS, unlike the PD-H-375TS not adapted homolog suppressed the growth of subcutaneous Colo320 tumors in nude mice without causing any side effects.ConclusionTaken together, here we present an optimized protocol for the rapid generation of tumor cell-specific adapted oncolytic CVB3 based on the oncolytic CVB3 strain PD-H. The protocol is promising for the generation of personalized OV for tumor therapy and has the potential to be applied to other OV.

Few-shot time series forecasting in a meta-learning framework

Time series forecasting has a wide range of applications in various fields. To eliminate the need for time series data volume, a meta-learning-based few-shot time series forecasting method is proposed. This method uses a residual stack module as its backbone and connects the residuals forward and backward through a multilayer fully connected network so that the model and the meta-learning framework can be seamlessly combined. The Empirical knowledge of different time-sequence tasks is obtained through meta-training. To enable fast adaptation to new prediction tasks, a small meta-network is introduced to adaptively and dynamically generate the learning rate and weight decay coefficient of each step in the network. This method can use sequences of different data distribution characteristics for cross-task learning, and each training task only needs a small number of time series to achieve sequence prediction for the target task. The results show that compared with the two baselines, the proposed method has improved performance on 67.07% and 58.53% of the evaluated tasks. Thus, this method can effectively alleviate the problems caused by insufficient data during training and has broad application prospects in the field of time series.

Bayesian Meta-Learning: Toward Fast Adaptation in Neural Network Positioning Techniques

Bayesian Meta-Learning: Toward Fast Adaptation in Neural Network Positioning Techniques