TMIC is an App Inventor extension for the deployment of ML models for image classification developed with Google Teachable Machine in educational settings. Google Teachable Machine, is an intuitive visual tool that provides workflow-oriented support for the development of ML models for image classification. Aiming at the usage of models developed with Google Teachable Machine, the extension TMIC enables the deployment of the trained models exported as TensorFlow.js to Google Cloud as part of App Inventor, one of the most popular block-based programming environments for teaching computing in K-12. The extension was created with the App Inventor extension framework based on the extension PIC and is available under the BSD 3 license. It can be used for teaching ML in K-12, in introductory courses in higher education or by anyone interested in creating intelligent apps with image classification. The extension TMIC is being developed by the initiative Computa\c{c}\~ao na Escola of the Department of Informatics and Statistics at the Federal University of Santa Catarina/Brazil as part of a research effort aiming at introducing AI education in K-12.

What would it take for a natural language model to understand a novel, such as The Lord of the Rings? Among other things, such a model must be able to: (a) identify and record new characters (entities) and their attributes as they are introduced in the text, and (b) identify subsequent references to the characters previously introduced and update their attributes. This problem of entity tracking is essential for language understanding, and thus, useful for a wide array of downstream applications in NLP such as question-answering, summarization. In this thesis, we focus on two key problems in relation to facilitating the use of entity tracking models: (i) scaling entity tracking models to long documents, such as a novel, and (ii) integrating entity tracking into language models. Applying language technologies to long documents has garnered interest recently, but computational constraints are a significant bottleneck in scaling up current methods. In this thesis, we argue that computationally efficient entity tracking models can be developed by representing entities with rich, fixed-dimensional vector representations derived from pretrained language models, and by exploiting the ephemeral nature of entities. We also argue for the integration of entity tracking into language models as it will allow for: (i) wider application given the current ubiquitous use of pretrained language models in NLP applications, and (ii) easier adoption since it is much easier to swap in a new pretrained language model than to integrate a separate standalone entity tracking model.

In Federated Learning (FL) of click-through rate (CTR) prediction, users' data is not shared for privacy protection. The learning is performed by training locally on client devices and communicating only model changes to the server. There are two main challenges: (i) the client heterogeneity, making FL algorithms that use the weighted averaging to aggregate model updates from the clients have slow progress and unsatisfactory learning results; and (ii) the difficulty of tuning the server learning rate with trial-and-error methodology due to the big computation time and resources needed for each experiment. To address these challenges, we propose a simple online meta-learning method to learn a strategy of aggregating the model updates, which adaptively weighs the importance of the clients based on their attributes and adjust the step sizes of the update. We perform extensive evaluations on public datasets. Our method significantly outperforms the state-of-the-art in both the speed of convergence and the quality of the final learning results.

This article studies the estimation of latent community memberships from pairwise interactions in a network of $N$ nodes, where the observed interactions can be of arbitrary type, including binary, categorical, and vector-valued, and not excluding even more general objects such as time series or spatial point patterns. As a generative model for such data, we introduce a stochastic block model with a general measurable interaction space $\mathcal S$, for which we derive information-theoretic bounds for the minimum achievable error rate. These bounds yield sharp criteria for the existence of consistent and strongly consistent estimators in terms of data sparsity, statistical similarity between intra- and inter-block interaction distributions, and the shape and size of the interaction space. The general framework makes it possible to study temporal and multiplex networks with $\mathcal S = \{0,1\}^T$, in settings where both $N \to \infty$ and $T \to \infty$, and the temporal interaction patterns are correlated over time. For temporal Markov interactions, we derive sharp consistency thresholds. We also present fast online estimation algorithms which fully utilise the non-binary nature of the observed data. Numerical experiments on synthetic and real data show that these algorithms rapidly produce accurate estimates even for very sparse data arrays.

We present BioSLAM, a lifelong SLAM framework for learning various new appearances incrementally and maintaining accurate place recognition for previously visited areas. Unlike humans, artificial neural networks suffer from catastrophic forgetting and may forget the previously visited areas when trained with new arrivals. For humans, researchers discover that there exists a memory replay mechanism in the brain to keep the neuron active for previous events. Inspired by this discovery, BioSLAM designs a gated generative replay to control the robot's learning behavior based on the feedback rewards. Specifically, BioSLAM provides a novel dual-memory mechanism for maintenance: 1) a dynamic memory to efficiently learn new observations and 2) a static memory to balance new-old knowledge. When combined with a visual-/LiDAR- based SLAM system, the complete processing pipeline can help the agent incrementally update the place recognition ability, robust to the increasing complexity of long-term place recognition. We demonstrate BioSLAM in two incremental SLAM scenarios. In the first scenario, a LiDAR-based agent continuously travels through a city-scale environment with a 120km trajectory and encounters different types of 3D geometries (open streets, residential areas, commercial buildings). We show that BioSLAM can incrementally update the agent's place recognition ability and outperform the state-of-the-art incremental approach, Generative Replay, by 24%. In the second scenario, a LiDAR-vision-based agent repeatedly travels through a campus-scale area on a 4.5km trajectory. BioSLAM can guarantee the place recognition accuracy to outperform 15\% over the state-of-the-art approaches under different appearances. To our knowledge, BioSLAM is the first memory-enhanced lifelong SLAM system to help incremental place recognition in long-term navigation tasks.

One of the most fundamental problems in machine learning is to compare examples: Given a pair of objects we want to return a value which indicates degree of (dis)similarity. Similarity is often task specific, and pre-defined distances can perform poorly, leading to work in metric learning. However, being able to learn a similarity-sensitive distance function also presupposes access to a rich, discriminative representation for the objects at hand. In this dissertation we present contributions towards both ends. In the first part of the thesis, assuming good representations for the data, we present a formulation for metric learning that makes a more direct attempt to optimize for the k-NN accuracy as compared to prior work. We also present extensions of this formulation to metric learning for kNN regression, asymmetric similarity learning and discriminative learning of Hamming distance. In the second part, we consider a situation where we are on a limited computational budget i.e. optimizing over a space of possible metrics would be infeasible, but access to a label aware distance metric is still desirable. We present a simple, and computationally inexpensive approach for estimating a well motivated metric that relies only on gradient estimates, discussing theoretical and experimental results. In the final part, we address representational issues, considering group equivariant convolutional neural networks (GCNNs). Equivariance to symmetry transformations is explicitly encoded in GCNNs; a classical CNN being the simplest example. In particular, we present a SO(3)-equivariant neural network architecture for spherical data, that operates entirely in Fourier space, while also providing a formalism for the design of fully Fourier neural networks that are equivariant to the action of any continuous compact group.

HONG KONG Reuters) - Zhang Meng had a breakdown last December. The 20-year-old found herself sobbing on the stairs of her dorm, driven to despair by repeated COVID lockdowns of her university campus in Beijing. The lockdowns had meant she was mostly confined to her room and unable to meet up with friends. There were also strict curbs on when she could visit the canteen or take a shower. Describing herself as someone who craves in-person social interaction, Zhang said the restrictions had "removed the safety net that was holding me up and I felt like my whole being was falling down".

Gadi Singer is Vice President and Director of Emergent AI Research at Intel Labs leading the development of the third wave of AI capabilities. In a series on the choices for capturing information and using knowledge in AI systems, I introduced the concept of an information-centric classification of AI systems as a complementary view to a processing-based classification such as Henry Kautz's taxonomy for neural symbolic computing . The classification emphasizes the high-level architectural choice related to information in the AI system. This blog will outline the third class in this classification and its promising role in supporting machine understanding, context-based decision making, and other aspects of higher machine intelligence. There is no access to additional information at test time.

NIR Calibration-Model Services Spectroscopy and Chemometrics News Weekly 33, 2022 NIRS NIR Spectroscopy MachineLearning Spectrometer Spectrometric Analytical Chemistry Chemical Analysis Lab Labs Laboratories Laboratory Software IoT Sensors QA QC Testing Quality LINK Spektroskopie und Chemometrie Neuigkeiten Wöchentlich 33, 2022 NIRS NIR Spektroskopie MachineLearning Spektrometer IoT Sensor Nahinfrarot Chemie Analytik Analysengeräte Analysentechnik Analysemethode Nahinfrarotspektroskopie Laboranalyse LINK Spettroscopia e Chemiometria Weekly News 33, 2022 NIRS NIR Spettroscopia MachineLearning analisi chimica Spettrale Spettrometro Chem IoT Sensore Attrezzatura analitica Laboratorio analisi prova qualità Analysesystem QualityControl LINK Near-Infrared Spectroscopy (NIRS) "Comparative Performance of NIR-Hyperspectral Imaging Systems" LINK "Near infrared spectroscopy calibration strategies to predict multiple nutritional parameters of pasture species from different functional groups" LINK "Near-infrared spectroscopy as a tool to assist Sargassum fusiforme quality grading: Harvest time discrimination and polyphenol prediction" LINK "Sensors : Using Vis-NIR Spectroscopy for Predicting Quality Compounds in Foods" LINK "Development of an amino acid sequence-dependent analytical method for peptides using near-infrared spectroscopy" LINK "NDT model study of crown pear based on near infrared spectroscopy" LINK "Analyzing the Water Confined in Hydrogel Using Near-Infrared Spectroscopy" LINK "Foods : Finite Element Analysis and Near-Infrared Hyperspectral Reflectance Imaging for the Determination of Blueberry Bruise Grading" LINK "Application of near infrared spectroscopy in sub-surface monitoring of petroleum contaminants in laboratory-prepared soils" LINK "Identification of multiple raisins by feature fusion combined with NIR spectroscopy" LINK " … of quality markers for quality control of Zanthoxylum nitidum using ultra-performance liquid chromatography coupled with near infrared spectroscopy" LINK "Karakterisasi Fitokimia Enkapsulasi Nira Tebu Powder dengan Menggunakan Varietas BL, PSDK-923, dan PSBM-901" LINK "Inside the Egg--Demonstrating Provenance Without the Cracking Using Near Infrared Spectroscopy" LINK "Organic resources from Madagascar: Dataset of chemical and near-infrared spectroscopy measurements" LINK "An alternative method for identification of industrial tomato hybrids using NIRS" LINK "Uniformity evaluation of stem distribution in cut tobacco and single cigarette by near infrared spectroscopy" LINK "A General and Scalable Vision Framework for Functional Near-Infrared Spectroscopy Classification" LINK "Near infrared spectroscopy for the pre-cure freezing discrimination of Montanera Iberian dry-cured lomito" LINK "Determination of Moisture and Protein Content in Living Mealworm Larvae (Tenebrio molitor L.) Using Near-Infrared Reflectance Spectroscopy (NIRS)" LINK "Towards Inline Prediction of Color Development for Wood Stained with Chemical Stains Using Near-Infrared Spectroscopy" LINK "Comparison Between Pure Component Modeling Approaches for Monitoring Pharmaceutical Powder Blends with Near-Infrared Spectroscopy in Continuous Manufacturing Schemes" LINK "Potential of NIRS technology for the determination of cannabinoid content in industrial hemp (Cannabis sativa L.)" LINK " A Variable Selection Method Based on Fast Nondominated Sorting Genetic Algorithm for Qualitative Discrimination of Near Infrared Spectroscopy" LINK "Scale invariance in fNIRS as a measurement of cognitive load" LINK "Quantification of Salicylates and Flavonoids in Poplar Bark and Leaves Based on IR, NIR, and Raman Spectra" LINK Infrared Spectroscopy (IR) and Near-Infrared Spectroscopy (NIR) "Near-infrared spectroscopy monitoring during endovascular treatment for acute ischaemic stroke" LINK "Keakuratan Teknologi Near Infrared Dalam Mengukur Dan Memetakan Bahan Organik Di Pulau Lombok" LINK "NearInfrared Spectroscopic Characterization of Cardiac and Renal Fibrosis in Fixed and Fresh Rat Tissue" LINK "Application of Fourier transform infrared spectroscopy (FTIR) techniques in the mid-IR (MIR) and near-IR (NIR) spectroscopy to determine n-alkane and long-chain alcohol contents in plant species and faecal samples" LINK Hyperspectral Imaging (HSI) "Detection Storage Time of Mild Bruise's Loquats Using Hyperspectral Imaging" LINK "Determination of plumpness for kernel of semen ziziphi spinosae use of hyperspectral transmittance imaging technology coupled with improved Otsu algorithm" LINK "Prediction of oil content in single maize kernel based on hyperspectral imaging and attention convolution neural network" LINK "Convolutional neural networks for mapping of lake sediment core particle size using hyperspectral imaging" LINK Spectral Imaging "Applied Sciences : Non-Invasive Monitoring of the Thermal and Morphometric Characteristics of Lettuce Grown in an Aeroponic System through Multispectral Image System" LINK Chemometrics and Machine Learning "Rapid quantification of goat milk adulteration with cow milk using Raman spectroscopy and chemometrics" LINK "Plants : Prediction of Oil Palm Yield Using Machine Learning in the Perspective of Fluctuating Weather and Soil Moisture Conditions: Evaluation of a Generic Workflow" LINK "Near Infrared Spectra Data Analysis by Using Machine Learning Algorithms" LINK "Applied Sciences : Deep-Learning Model Selection and Parameter Estimation from a Wind Power Farm in Taiwan" LINK "Predicting maize LAI in partial least square modeling by continuous wavelet transform and uninformative variable elimination from canopy spectral reflectance" LINK "Machine Learning Algorithms for Protein Physicochemical Component Prediction Using Near Infrared Spectroscopy in Chickpea Germplasm" LINK "NIR Validation and Calibration of Proximate components of available Corn Silage in Bangladesh." So interested people will connect.

In this article, I am going to map out the things you need to do to become a Data Scientist. This article may solely be for beginners, however, there may be a thing or two that current Junior Data Scientists may have missed out on. This is where I am here to help fill in those gaps so that you don't have to feel imposter syndrome or lack of confidence on your data science journey. I will be taking you through the steps - it is a roadmap at the end of the day. Python is one of the most popular programming languages today and more and more people are adopting it due to its simplicity.