DOCSLIB.ORG

Présentation Powerpoint

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Présentation Powerpoint « Meetup Data Science » Mercredi 4 mars 2020 Comment l’IA démultiplie les fonctions cognitives ? A variant of machine learning engineer is called Deep Learning engineer. This role requires deep learning knowledge in addition to the skills profile Jean-Marie PRIGENT (Modeling, Deployment, Data Engineering). It focuses on applications, usually powered by deep ML Engineer learning, such as speech recognition, natural language processing, and computer vision. Hence, it Altran Brest requires skills specific to deep learning projects such as understanding and using various neural network architectures such as fully connected networks, CNNs, and RNNs. P as Passionately curious... Big Data and DL but not only… Drones, FPV, CV, Maker, 3D Printer, Electronics, DonkeyCar, Edge, ... linkedin.com/in/jmprigent Machine Learning Ecosystem Machine Learning Languages: Data Processing: - Python / R / (C++) - BIG Data framework (Cloudera/HDP/Oozie/Pig/Spark/ General Machine Learning Frameworks Scala ) - Numpy - Apache Airflow, NIFI - Scikit-Learn - NLTK, Spacy Hardware Training: - CPU, GPU, TPU, Cloud Data Analysis and Visualisation tools - Distrubuted (Spark, Kubeflow) - Pandas - Federated Learning (WO - Matplotlib centralized server) - Jupyter Notebook Inference ML frameworks for neural networks - Desktop, server … modelling - Mobile - Tensorflow / Tensorboard - Edge device (VPU: Intel NCS2, - Keras GPU: Jetson Nano & TPU: Coral - Pytorch dev board, Coral stick) - (Caffe2, mxnet) What is Deep Learning ? Deep learning is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised. Deep learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolutional neural networks have been applied to fields including computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance Deep Learning : “a technique for implementing Machine Learning” Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Le Deep Learning dans l’Univers de l’IA... Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Le Deep Learning dans l’Univers de l’IA... Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Some dates in the field of IA 1980 – Kunihiko Fukushima built the ‘neocognitron’, the precursor of modern Convolutional Neural Networks. 2001 – Two researchers at MIT introduced the first face detection framework (Viola-Jones) that works in real-time. 2009 – Google started testing robot cars on roads. 2010 – Google released Goggles, an image recognition app for searches based on pictures taken by mobile devices. 2010 – To help tag photos, Facebook began using facial recognition. 2011 – Facial recognition was used to help confirm the identity of Osama bin Laden after he is killed in a US raid. 2012 – Google Brain’s neural network recognized pictures of cats using a deep learning algorithm. 2015 – Google launched open-source Machine learning-system TensorFlow. 2016 – Google DeepMind’s AlphaGo algorithm beat the world Go champion. 2017 – Apple released the iPhone X in 2017, advertising face recognition as one of its primary new features. 2018 – Alibaba’s AI model scored better than humans in a Stanford University reading and comprehension test. 2018 – Amazon sold its real time face recognition system Rekognition to police departments. 2019 – The Indian government announced a facial recognition plan allowing police officers to search images through mobile app. 2019 – The US added four of China’s leading AI start-ups to a trade blacklist. 2019 – The UK High Court ruled that the use of automatic facial recognition technology to search for people in crowds is lawful. 2025 – By this time, regulation in FR will significantly diverge between China and US/Europe. 2030 – At least 60% of countries globally will be using AI surveillance technology (it is currently 43% according to CEIP). This is an edited extract from the Computer Vision – Thematic Research report produced by GlobalData Thematic Research. https://www.verdict.co.uk/computer-vision-timeline/ Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Apprentissage supervisé “L’objectif de l’apprentissage supervisé est d’apprendre une fonction qui, à partir d’un échantillon de données et des résultats souhaités, se rapproche le mieux de la relation entre entrée et sortie observable dans les données.” -> Y = f (X) L’apprentissage supervisé est généralement effectué dans le contexte de la classification et de la régression. Classification: Un problème de classification survient lorsque la variable de sortie est une catégorie, telle que «rouge», «bleu» ou «maladie» et «pas de maladie». Régression: Un problème de régression se pose lorsque la variable de sortie est une valeur réelle, telle que «dollars» ou «poids». source: https://le-datascientist.fr/apprentissage-supervise-vs-non-supervise Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Apprentissage non supervisé “L’apprentissage non supervisé (Unsupervised Learning) consiste à ne disposer que de données d’entrée (X) et pas de variables de sortie correspondantes. L’objectif est de modéliser la structure ou la distribution sous-jacente dans les données afin d’en apprendre davantage sur les données. On l’appelle apprentissage non supervisé car, contrairement à l’apprentissage supervisé, il n’y a pas de réponse correcte ni d’enseignant. Les algorithmes sont laissés à leurs propres mécanismes pour découvrir et présenter la structure intéressante des données.” Regroupement ou clustering: l’objectif est de séparer les groupes ayant des traits similaires et de les assigner en grappes. Association: consiste à découvrir des relations intéressantes entre des variables dans de grandes bases de données. Par exemple, les personnes qui achètent une nouvelle maison ont aussi tendance à acheter de nouveaux meubles source: https://le-datascientist.fr/apprentissage-supervise-vs-non-supervise Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Apprentissage semi supervisé “Les problèmes pour lesquels vous avez une grande quantité de données d’entrée (X) et que seules certaines données sont étiquetées (Y) sont appelés problèmes d’apprentissage semi-supervisés. Par conséquent, ces problèmes se situent entre l’apprentissage supervisé et l’apprentissage non supervisé” Le Deep Learning rentre dans la catégorie “supervisé” pour la majorité des cas et plus récemment semi supervisé avec les GAN. Le (Deep) Reinforcement Learning rentre dans la categorie non supervisé source: https://le-datascientist.fr/apprentissage-supervise-vs-non-supervise Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent A Visual and Interactive Guide to the Basics of Neural Networks...in a nutshell source: jay Alammar Blog Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent A Visual and Interactive Guide to the Basics of Neural Networks...in a nutshell Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent A Visual and Interactive Guide to the Basics of Neural Networks...in a nutshell Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent A Visual and Interactive Guide to the Basics of Neural Networks...in a nutshell Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent What convolution neural network see... Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Some vocab in Computer Vision tasks 4 differents tasks in CV: - image classification - object detection - semantic segmentation - instance segmentation Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Imaging Applications Deep Learning has applications in all sectors of activity. It is a major issue for the industrial and scientific sectors and the safety of goods and people. Among these uses are in particular : - Image recognition (classification, localization and segmentation), - Description of scenes, - Facial recognition (security), - Optical Character Recognition (OCR), - Content-Based Images Retrieval (CBIR) - Medical Imaging (biology, histology, radiology), - Synthetic image generation (GAN), - Emotion detection, - Detection of age and gender, … Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent NLP-NLU Applications NLP iis becoming more democratic, previously reserved for researchers. The advent of personal assistants (Siri, Alexa, Google Home) and its high level of adoption proves the maturity of this technology. Studies prove that using a text transcriber is 3 times faster than writing the text. Among the cases of use are the following: - Chatbots - Spam detection / Spam filter avoidance - Sentiment analysis (consumer opinions, customer opinions) - E-reputation - Automated translation - Subtitling of video sequences (Speech-to-Text) - Voice User Interface (VUI) (Siri, Alexa, Ok Google) … Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Get datas … and Training Neural Network tensorboard UI Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent Training sample on Fashion-MNIST under Colab Fashion Mnist Meetup Data Sciences - Brest is IA - 2020-03-04 - Jean-Marie Prigent 3/ Inference
Load more

Recommended publications
  • CS855 Pattern Recognition and Machine Learning Homework 3 A.Aziz Altowayan
    CS855 Pattern Recognition and Machine Learning Homework 3 A.Aziz Altowayan Problem Find three recent (2010 or newer) journal articles of conference papers on pattern recognition applications using feed-forward neural networks with backpropagation learning that clearly describe the design of the neural network { number of layers and number of units in each layer { and the rationale for the design. For each paper, describe the neural network, the reasoning behind the design, and include images of the neural network when available. Answer 1 The theme of this ansewr is Deep Neural Network 2 (Deep Learning or multi-layer deep architecture). The reason is that in recent years, \Deep learning technology and related algorithms have dramatically broken landmark records for a broad range of learning problems in vision, speech, audio, and text processing." [1] Deep learning models are a class of machines that can learn a hierarchy of features by building high-level features from low-level ones, thereby automating the process of feature construction [2]. Following are three paper in this topic. Paper1: D. C. Ciresan, U. Meier, J. Schmidhuber. \Multi-column Deep Neural Networks for Image Classifica- tion". IEEE Conf. on Computer Vision and Pattern Recognition CVPR 2012. Feb 2012. arxiv \Work from Swiss AI Lab IDSIA" This method is the first to achieve near-human performance on MNIST handwriting dataset. It, also, outperforms humans by a factor of two on the traffic sign recognition benchmark. In this paper, the network model is Deep Convolutional Neural Networks. The layers in their NNs are comparable to the number of layers found between retina and visual cortex of \macaque monkeys".
    [Show full text]
  • Deep Neural Network Models for Sequence Labeling and Coreference Tasks
    Federal state autonomous educational institution for higher education ¾Moscow institute of physics and technology (national research university)¿ On the rights of a manuscript Le The Anh DEEP NEURAL NETWORK MODELS FOR SEQUENCE LABELING AND COREFERENCE TASKS Specialty 05.13.01 - ¾System analysis, control theory, and information processing (information and technical systems)¿ A dissertation submitted in requirements for the degree of candidate of technical sciences Supervisor: PhD of physical and mathematical sciences Burtsev Mikhail Sergeevich Dolgoprudny - 2020 Федеральное государственное автономное образовательное учреждение высшего образования ¾Московский физико-технический институт (национальный исследовательский университет)¿ На правах рукописи Ле Тхе Ань ГЛУБОКИЕ НЕЙРОСЕТЕВЫЕ МОДЕЛИ ДЛЯ ЗАДАЧ РАЗМЕТКИ ПОСЛЕДОВАТЕЛЬНОСТИ И РАЗРЕШЕНИЯ КОРЕФЕРЕНЦИИ Специальность 05.13.01 – ¾Системный анализ, управление и обработка информации (информационные и технические системы)¿ Диссертация на соискание учёной степени кандидата технических наук Научный руководитель: кандидат физико-математических наук Бурцев Михаил Сергеевич Долгопрудный - 2020 Contents Abstract 4 Acknowledgments 6 Abbreviations 7 List of Figures 11 List of Tables 13 1 Introduction 14 1.1 Overview of Deep Learning . 14 1.1.1 Artificial Intelligence, Machine Learning, and Deep Learning . 14 1.1.2 Milestones in Deep Learning History . 16 1.1.3 Types of Machine Learning Models . 16 1.2 Brief Overview of Natural Language Processing . 18 1.3 Dissertation Overview . 20 1.3.1 Scientific Actuality of the Research . 20 1.3.2 The Goal and Task of the Dissertation . 20 1.3.3 Scientific Novelty . 21 1.3.4 Theoretical and Practical Value of the Work in the Dissertation . 21 1.3.5 Statements to be Defended . 22 1.3.6 Presentations and Validation of the Research Results .
    [Show full text]
  • Voice Interfaces
    VIEW POINT VOICE INTERFACES Abstract A voice-user interface (VUI) makes human interaction with computers possible through a voice/speech platform in order to initiate an automated service or process. This Point of View explores the reasons behind the rise of voice interface, key challenges enterprises face in voice interface adoption and the solution to these. Are We Ready for Voice Interfaces? Let’s get talking! IO showed the new promise of voice offering integrations with their Voice interfaces. Assistants. Since Apple integration with Siri, voice interfaces has significantly Almost all the big players (Google, Apple, As per industry forecasts, over the next progressed. Echo and Google Home Microsoft) have ‘office productivity’ decade, 8 out of every 10 people in the have demonstrated that we do not need applications that are being adopted by world will own a device (a smartphone or a user interface to talk to computers businesses (Microsoft and their Office some kind of assistant) which will support and have opened-up a new channel for Suite already have a big advantage here, voice based conversations in native communication. Recent demos of voice but things like Google Docs and Keynote language. Just imagine the impact! based personal assistance at Google are sneaking in), they have also started Voice Assistant Market USD~7.8 Billion CAGR ~39% Market Size (USD Billion) 2016 2017 2018 2019 2020 2021 2022 2023 The Sudden Interest in Voice Interfaces Although voice technology/assistants Voice Recognition Accuracy Convenience – speaking vs typing have been around in some shape or form Voice Recognition accuracy continues to Humans can speak 150 words per minute for many years, the relentless growth of improve as we now have the capability to vs the typing speed of 40 words per low-cost computational power—and train the models using neural networks minute.
    [Show full text]
  • NLP-5X Product Brief
    NLP-5x Natural Language Processor With Motor, Sensor and Display Control The NLP-5x is Sensory’s new Natural Language Processor targeting consumer electronics. The NLP-5x is designed to offer advanced speech recognition, text-to-speech (TTS), high quality music and speech synthesis and robotic control to cost-sensitive high volume products. Based on a 16-bit DSP, the NLP-5x integrates digital and analog processing blocks and a wide variety of communication interfaces into a single chip solution minimizing the need for external components. The NLP-5x operates in tandem with FluentChip™ firmware - an ultra- compact suite of technologies that enables products with up to 750 seconds of compressed speech, natural language interface grammars, TTS synthesis, Truly Hands-Free™ triggers, multiple speaker dependent and independent vocabularies, high quality stereo music, speaker verification (voice password), robotics firmware and all application code built into the NLP-5x as a single chip solution. The NLP-5x also represents unprecedented flexibility in application hardware designs. Thanks to the highly integrated architecture, the most cost-effective voice user interface (VUI) designs can be built with as few additional parts as a clock crystal, speaker, microphone, and few resistors and capacitors. The same integration provides all the necessary control functions on-chip to enable cost-effective man-machine interfaces (MMI) with sensing technologies, and complex robotic products with motors, displays and interactive intelligence. Features BROAD
    [Show full text]
  • A Guide to Chatbot Terminology
    Machine Language A GUIDE TO CHATBOT TERMINOLOGY Decision Trees The most basic chatbots are based on tree-structured flowcharts. Their responses follow IF/THEN scripts that are linked to keywords and buttons. Natural Language Processing (NLP) A computer’s ability to detect human speech, recognize patterns in conversation, and turn text into speech. Natural Language Understanding A computer’s ability to determine intent, especially when what is said doesn’t quite match what is meant. This task is much more dicult for computers than Natural Language Processing. Layered Communication Human communication is complex. Consider the intricacies of: • Misused phrases • Intonation • Double meanings • Passive aggression • Poor pronunciation • Regional dialects • Subtle humor • Speech impairments • Non-native speakers • Slang • Syntax Messenger Chatbots Messenger chatbots reside within the messaging applications of larger digital platforms (e.g., Facebook, WhatsApp, Twitter, etc.) and allow businesses to interact with customers on the channels where they spend the most time. Chatbot Design Programs There’s no reason to design a messenger bot from scratch. Chatbot design programs help designers make bots that: • Can be used on multiple channels • (social, web, apps) • Have custom design elements • (response time, contact buttons, • images, audio, etc.) • Collect payments • Track analytics (open rates, user • retention, subscribe/unsubscribe • rates) • Allow for human takeover when • the bot’s capabilities are • surpassed • Integrate with popular digital • platforms (Shopify, Zapier, Google • Site Search, etc.) • Provide customer support when • issues arise Voice User Interface A voice user interface (VUI) allows people to interact with a computer through spoken commands and questions. Conversational User Interface Like a voice user interface, a conversational user interface (CUI) allows people to control a computer with speech, but CUI’s dier in that they emulate the nuances of human conversation.
    [Show full text]
  • Voice User Interface on the Web Human Computer Interaction Fulvio Corno, Luigi De Russis Academic Year 2019/2020 How to Create a VUI on the Web?
    Voice User Interface On The Web Human Computer Interaction Fulvio Corno, Luigi De Russis Academic Year 2019/2020 How to create a VUI on the Web? § Three (main) steps, typically: o Speech Recognition o Text manipulation (e.g., Natural Language Processing) o Speech Synthesis § We are going to start from a simple application to reach a quite complex scenario o by using HTML5, JS, and PHP § Reminder: we are interested in creating an interactive prototype, at the end 2 Human Computer Interaction Weather Web App A VUI for "chatting" about the weather Base implementation at https://github.com/polito-hci-2019/vui-example 3 Human Computer Interaction Speech Recognition and Synthesis § Web Speech API o currently a draft, experimental, unofficial HTML5 API (!) o https://wicg.github.io/speech-api/ § Covers both speech recognition and synthesis o different degrees of support by browsers 4 Human Computer Interaction Web Speech API: Speech Recognition § Accessed via the SpeechRecognition interface o provides the ability to recogniZe voice from an audio input o normally via the device's default speech recognition service § Generally, the interface's constructor is used to create a new SpeechRecognition object § The SpeechGrammar interface can be used to represent a particular set of grammar that your app should recogniZe o Grammar is defined using JSpeech Grammar Format (JSGF) 5 Human Computer Interaction Speech Recognition: A Minimal Example const recognition = new window.SpeechRecognition(); recognition.onresult = (event) => { const speechToText = event.results[0][0].transcript;
    [Show full text]
  • Eindversie-Paper-Rianne-Nieland-2057069
    Talking to Linked Data: Comparing voice interfaces for general­purpose data Master thesis of Information Sciences Rianne Nieland Vrije Universiteit Amsterdam [email protected] ABSTRACT ternet access (Miniwatts Marketing Group, 2012) and People in developing countries cannot access informa- 31.1% is literate (UNESCO, 2010). tion on the Web, because they have no Internet access and are often low literate. A solution could be to pro- A solution to the literacy and Internet access problem vide voice-based access to data on the Web by using the is to provide voice-based access to the Internet by us- GSM network. Related work states that Linked Data ing the GSM network (De Boer et al., 2013). 2G mobile could be a useful input source for such voice interfaces. phones are digital mobile phones that use the GSM net- work (Fendelman, 2014). In Africa the primary mode The aim of this paper is to find an efficient way to make of telecommunication is mobile telephony (UNCTAD, general-purpose data, like Wikipedia information, avail- 2007). able using voice interfaces for GSM. To achieve this, we developed two voice interfaces, one for Wikipedia This paper is about how information on the Web ef- and one for DBpedia, by doing requirements elicitation ficiently can be made available using voice interfaces from literature and developing a voice user interface and for GSM. We developed two voice interfaces, one us- conversion algorithms for Wikipedia and DBpedia con- ing Wikipedia and the other using DBpedia. In this cepts. With user tests the users evaluated the two voice paper we see Wikipedia and DBpedia as two different interfaces, to be able to compare them.
    [Show full text]
  • Voice Assistants and Smart Speakers in Everyday Life and in Education
    Informatics in Education, 2020, Vol. 19, No. 3, 473–490 473 © 2020 Vilnius University, ETH Zürich DOI: 10.15388/infedu.2020.21 Voice Assistants and Smart Speakers in Everyday Life and in Education George TERZOPOULOS, Maya SATRATZEMI Department of Applied Informatics, University of Macedonia, Thessaloniki, Greece Email: [email protected], [email protected] Received: November 2019 Abstract. In recent years, Artificial Intelligence (AI) has shown significant progress and its -po tential is growing. An application area of AI is Natural Language Processing (NLP). Voice as- sistants incorporate AI by using cloud computing and can communicate with the users in natural language. Voice assistants are easy to use and thus there are millions of devices that incorporates them in households nowadays. Most common devices with voice assistants are smart speakers and they have just started to be used in schools and universities. The purpose of this paper is to study how voice assistants and smart speakers are used in everyday life and whether there is potential in order for them to be used for educational purposes. Keywords: artificial intelligence, smart speakers, voice assistants, education. 1. Introduction Emerging technologies like virtual reality, augmented reality and voice interaction are reshaping the way people engage with the world and transforming digital experiences. Voice control is the next evolution of human-machine interaction, thanks to advances in cloud computing, Artificial Intelligence (AI) and the Internet of Things (IoT). In the last years, the heavy use of smartphones led to the appearance of voice assistants such as Apple’s Siri, Google’s Assistant, Microsoft’s Cortana and Amazon’s Alexa.
    [Show full text]
  • Arxiv:2103.13076V1 [Cs.CL] 24 Mar 2021
    Finetuning Pretrained Transformers into RNNs Jungo Kasai♡∗ Hao Peng♡ Yizhe Zhang♣ Dani Yogatama♠ Gabriel Ilharco♡ Nikolaos Pappas♡ Yi Mao♣ Weizhu Chen♣ Noah A. Smith♡♢ ♡Paul G. Allen School of Computer Science & Engineering, University of Washington ♣Microsoft ♠DeepMind ♢Allen Institute for AI {jkasai,hapeng,gamaga,npappas,nasmith}@cs.washington.edu {Yizhe.Zhang, maoyi, wzchen}@microsoft.com [email protected] Abstract widely used in autoregressive modeling such as lan- guage modeling (Baevski and Auli, 2019) and ma- Transformers have outperformed recurrent chine translation (Vaswani et al., 2017). The trans- neural networks (RNNs) in natural language former makes crucial use of interactions between generation. But this comes with a signifi- feature vectors over the input sequence through cant computational cost, as the attention mech- the attention mechanism (Bahdanau et al., 2015). anism’s complexity scales quadratically with sequence length. Efficient transformer vari- However, this comes with significant computation ants have received increasing interest in recent and memory footprint during generation. Since the works. Among them, a linear-complexity re- output is incrementally predicted conditioned on current variant has proven well suited for au- the prefix, generation steps cannot be parallelized toregressive generation. It approximates the over time steps and require quadratic time complex- softmax attention with randomized or heuris- ity in sequence length. The memory consumption tic feature maps, but can be difficult to train in every generation step also grows linearly as the and may yield suboptimal accuracy. This work aims to convert a pretrained transformer into sequence becomes longer. This bottleneck for long its efficient recurrent counterpart, improving sequence generation limits the use of large-scale efficiency while maintaining accuracy.
    [Show full text]
  • Integrating a Voice User Interface Into a Virtual Therapy Platform Yun Liu Lu Wang William R
    Integrating a Voice User Interface into a Virtual Therapy Platform Yun Liu Lu Wang William R. Kearns University of Washington, Seattle, University of Washington, Seattle, University of Washington, Seattle, WA 98195, USA WA 98195, USA WA 98195, USA [email protected] [email protected] [email protected] Linda E Wagner John Raiti Yuntao Wang University of Washington, Seattle, University of Washington, Seattle, Tsinghua University, Beijing 100084, WA 98195, USA WA 98195, USA China & University of Washington, [email protected] [email protected] WA 98195, USA [email protected] Weichao Yuwen University of Washington, Tacoma, WA 98402, USA [email protected] ABSTRACT ACM Reference Format: More than 1 in 5 adults in the U.S. serving as family caregivers are Yun Liu, Lu Wang, William R. Kearns, Linda E Wagner, John Raiti, Yuntao Wang, and Weichao Yuwen. 2021. Integrating a Voice User Interface into a the backbones of the healthcare system. Caregiving activities sig- Virtual Therapy Platform. In CHI Conference on Human Factors in Computing nifcantly afect their physical and mental health, sleep, work, and Systems Extended Abstracts (CHI ’21 Extended Abstracts), May 08–13, 2021, family relationships over extended periods. Many caregivers tend Yokohama, Japan. ACM, New York, NY, USA, 6 pages. https://doi.org/10. to downplay their own health needs and have difculty accessing 1145/3411763.3451595 support. Failure to maintain their own health leads to diminished ability in providing high-quality care to their loved ones. Voice user interfaces (VUIs) hold promise in providing tailored support 1 INTRODUCTION family caregivers need in maintaining their own health, such as Chronic diseases, such as diabetes and cancer, are the leading causes fexible access and handsfree interactions.
    [Show full text]
  • A Survey Paper on Convolutional Neural Network
    A Survey Paper on Convolutional Neural Network 1Ekta Upadhyay, 2Ranjeet Singh, 3Pallavi Upadhyay 1.1Department of Information Technology, 2.1Department of Computer Science Engineering 3.1Department of Information Technology, Buddha Institute of Technology, Gida, Gorakhpur, India Abstract In this era use of machines are growing promptly in every field such as pattern recognition, image, video processing project that can mimic like human cerebral network function and to achieve this Convolutional Neural Network of deep learning algorithm helps to train large datasets with millions of parameters of 2d image to provide desirable output using filters. Going through the convolutional layer then pooling layer and in last fully connected layer, Images becomes more effective how many times it filters become better than other. In this article we are going through the basic of Convolution Neural Network and its working process. Keywords-Deep Learning, Convolutional Neural Network, Handwritten digit recognition, MNIST, Pooling. 1- Introduction In the world of technology deep learning has become one of the most aspect in the field of machine. Deep learning which is sub-field of Artificial Learning that focuses on creating large Neural Network Model which provides accuracy in the field of data processing decision. social media apps like Instagram, twitter Google, Microsoft and many other apps with million users having multiple features like face recognition, some apps for handwriting recognition. Which is machine learning problem to recognize clearly[3], as we know machines are man-made and machines does not have minds or visual cortex to understands or see the real word entity, so to understand the real world in 1960 human create a theorem named Convolutional neural network of deep learning algorithm that make machine much more understandable.
    [Show full text]
  • Countering Terrorism Online with Artificial Intelligence an Overview for Law Enforcement and Counter-Terrorism Agencies in South Asia and South-East Asia
    COUNTERING TERRORISM ONLINE WITH ARTIFICIAL INTELLIGENCE AN OVERVIEW FOR LAW ENFORCEMENT AND COUNTER-TERRORISM AGENCIES IN SOUTH ASIA AND SOUTH-EAST ASIA COUNTERING TERRORISM ONLINE WITH ARTIFICIAL INTELLIGENCE An Overview for Law Enforcement and Counter-Terrorism Agencies in South Asia and South-East Asia A Joint Report by UNICRI and UNCCT 3 Disclaimer The opinions, findings, conclusions and recommendations expressed herein do not necessarily reflect the views of the Unit- ed Nations, the Government of Japan or any other national, regional or global entities involved. Moreover, reference to any specific tool or application in this report should not be considered an endorsement by UNOCT-UNCCT, UNICRI or by the United Nations itself. The designation employed and material presented in this publication does not imply the expression of any opinion whatsoev- er on the part of the Secretariat of the United Nations concerning the legal status of any country, territory, city or area of its authorities, or concerning the delimitation of its frontiers or boundaries. Contents of this publication may be quoted or reproduced, provided that the source of information is acknowledged. The au- thors would like to receive a copy of the document in which this publication is used or quoted. Acknowledgements This report is the product of a joint research initiative on counter-terrorism in the age of artificial intelligence of the Cyber Security and New Technologies Unit of the United Nations Counter-Terrorism Centre (UNCCT) in the United Nations Office of Counter-Terrorism (UNOCT) and the United Nations Interregional Crime and Justice Research Institute (UNICRI) through its Centre for Artificial Intelligence and Robotics.
    [Show full text]