The document provides an overview of machine learning and deep learning concepts. It begins with definitions of artificial intelligence, machine learning, and deep learning. It then discusses different machine learning systems including supervised, unsupervised, semi-supervised, and reinforcement learning. Deep learning frameworks like TensorFlow, Keras, PyTorch, Caffe2, Sonnet, MXNet, Gluon, CNTK, and Chainer are also introduced. The document is intended as an introduction for attendees of a GDG Baku meetup on machine learning and deep learning.
The goal of this course is to offer data science and fintech enthusiasts a hand-on practical case study to understand the power of Data Science, ML and AI in Finance. We discuss two case studies; An NLP case study and a Credit Risk case study to reinforce concepts
Credit Risk Introduction and Pre-class preparation
Pre-class reading. We will be using the Lending club data set to build a credit risk model using machine learning techniques. This workshop was be delivered in Boston and Online by Sri Krishnamurthy.
Natural language processing (NLP) is an area of artificial intelligence that helps computers understand and interpret human language. Innovations in Artificial intelligence, deep learning and compuational hardware is helping make major strides in NLP research. While the applications are many, it is important to understand the kinds of problems NLP techniques can help solve.
In this master class, we will introduce ten key NLP techniques that are predominantly used in the industry.
- Question Answering
- Neural Machine Translation
- Topic Summarization
- Natural Language Inference
- Semantic Role Labeling
- Text Classification
- Sentiment Analysis
- Relation extraction
- Goal-Oriented Dialogue
- Semantic Parsing
We will also illustrate a case study on NLP in Python using the QuSandbox.
Innovations in technology has revolutionized financial services to an extent that large financial institutions like Goldman Sachs are claiming to be technology companies! It is no secret that technological innovations like Data science and AI are changing fundamentally how financial products are created, tested and delivered. While it is exciting to learn about technologies themselves, there is very little guidance available to companies and financial professionals should retool and gear themselves towards the upcoming revolution.
In this master class, we will discuss key innovations in Data Science and AI and connect applications of these novel fields in forecasting and optimization. Through case studies and examples, we will demonstrate why now is the time you should invest to learn about the topics that will reshape the financial services industry of the future!
Topics for the Masterclass
- Learning Data science in 10 steps
RAPIDS is a suite of open source software libraries and APIs gives you the ability to execute end-to-end data science and analytics pipelines entirely on GPUs.In this workshop, we will:
1. Introduce Rapids.ai & GPUs
2. Illustrate why GPUs are critical for machine learning and AI applications
3. Demonstrate common machine learning algorithms such as Regression, KNN,SGD etc. using RAPIDS on the QuSandbox
This is the talk given at the Faculty of Information Technology, Monash University on 19/08/2020. It covers our recent research on the topics of learning to reason, including dual-process theory, visual reasoning and neural memories.
The goal of this course is to offer data science and fintech enthusiasts a hand-on practical case study to understand the power of Data Science, ML and AI in Finance. We discuss two case studies; An NLP case study and a Credit Risk case study to reinforce concepts
Credit Risk Introduction and Pre-class preparation
Pre-class reading. We will be using the Lending club data set to build a credit risk model using machine learning techniques. This workshop was be delivered in Boston and Online by Sri Krishnamurthy.
Natural language processing (NLP) is an area of artificial intelligence that helps computers understand and interpret human language. Innovations in Artificial intelligence, deep learning and compuational hardware is helping make major strides in NLP research. While the applications are many, it is important to understand the kinds of problems NLP techniques can help solve.
In this master class, we will introduce ten key NLP techniques that are predominantly used in the industry.
- Question Answering
- Neural Machine Translation
- Topic Summarization
- Natural Language Inference
- Semantic Role Labeling
- Text Classification
- Sentiment Analysis
- Relation extraction
- Goal-Oriented Dialogue
- Semantic Parsing
We will also illustrate a case study on NLP in Python using the QuSandbox.
Innovations in technology has revolutionized financial services to an extent that large financial institutions like Goldman Sachs are claiming to be technology companies! It is no secret that technological innovations like Data science and AI are changing fundamentally how financial products are created, tested and delivered. While it is exciting to learn about technologies themselves, there is very little guidance available to companies and financial professionals should retool and gear themselves towards the upcoming revolution.
In this master class, we will discuss key innovations in Data Science and AI and connect applications of these novel fields in forecasting and optimization. Through case studies and examples, we will demonstrate why now is the time you should invest to learn about the topics that will reshape the financial services industry of the future!
Topics for the Masterclass
- Learning Data science in 10 steps
RAPIDS is a suite of open source software libraries and APIs gives you the ability to execute end-to-end data science and analytics pipelines entirely on GPUs.In this workshop, we will:
1. Introduce Rapids.ai & GPUs
2. Illustrate why GPUs are critical for machine learning and AI applications
3. Demonstrate common machine learning algorithms such as Regression, KNN,SGD etc. using RAPIDS on the QuSandbox
This is the talk given at the Faculty of Information Technology, Monash University on 19/08/2020. It covers our recent research on the topics of learning to reason, including dual-process theory, visual reasoning and neural memories.
Full day lectures @International University, HCM City, Vietnam, May 2019. Review of AI in 2019; outlook into the future; empirical research in AI; introduction to AI research at Deakin University
Machine Learning has become a must to improve insight, quality and time to market. But it's also been called the 'high interest credit card of technical debt' with challenges in managing both how it's applied and how its results are consumed.
Machine learning with Big Data power point presentationDavid Raj Kanthi
This is an article made form the articles of IEEE published in the year 2017
The following presentation has the slides for the Title called the
Machine Learning with Big data. that following presentation which has the challenges and approaches of machine learning with big data.
The integration of the Big Data with Machine Learning has so many challenges that Big data has and what is the approach made by the machine learning mechanism for those challenges.
Computational Rationality I - a Lecture at Aalto University by Antti OulasvirtaAalto University
This 2-hour lecture looks at the emerging field of Computational Rationality. Lecture given March 12, 2018, for the Aalto University Master's level course on "Probabilistic Programming and Reinforcement Learning for Cognition and Interaction." Based on: Gershman et al 2015 Science, Lewis et al 2014 Topics in Cog Sci, and Gershman & Daw 2017 Annu Rev Psych
Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...Analytics India Magazine
Most organizations understand the predictive power and the potential gains from AIML, but AI and ML are still now a black box technology for them. While deep learning and neural networks can provide excellent inputs to businesses, leaders are challenged to use them because of the complete blind faith required to ‘trust’ AI. In this talk we will use the latest technological developments from researchers, the US defense department, and the industry to unbox the black box and provide businesses a clear understanding of the policy levers that they can pull, why, and by how much, to make effective decisions?
Why is image analytics Important? What good can come of caption generation or image descriptions? And how does Data Science & Machine learning techniques work on Image Analytics and to what purpose? We see how it works for the retail industry and for the Healthcare industry. What more? Take a look...
GRC 2020 - IIA - ISACA Machine Learning Monitoring, Compliance and GovernanceAndrew Clark
With Machine Learning (ML) taking on a more significant role in decision making, ML is becoming a risk management
and compliance issue. In light of increasing regulatory scrutiny, companies deploying ML must ensure that they have a
robust monitoring and compliance program. This presentation will provide context around relevant regulations, outline
critical risks and mitigating controls for ML, and provide an overview of monitoring and governance best practices.
This PPT Programming for data science in python mainly focus on importance of Python programming language in Python it explains the characteristic features of the programming language, its pros and cons and its applications.
machine learning in the age of big data: new approaches and business applicat...Armando Vieira
Presentation at University of Lisbon on Machine Learning and big data.
Deep learning algorithms and applications to credit risk analysis, churn detection and recommendation algorithms
As machine learning has is permeating more and more industries and businesses, the need for audit professionals to provide assurance over machine learning is growing. Andrew's presentation will provide an audit-centric overview of machine learning and present a framework for how to begin auditing machine learning in your organization.
QU Speaker Series - Session 3
https://qusummerschool.splashthat.com
A conversation with Quants, Thinkers and Innovators all challenged to innovate in turbulent times!
Join QuantUniversity for a complimentary summer speaker series where you will hear from Quants, innovators, startups and Fintech experts on various topics in Quant Investing, Machine Learning, Optimization, Fintech, AI etc.
Topic: Machine Learning and Model Risk (With a focus on Neural Network Models)
All models are wrong and when they are wrong they create financial or non-financial risks. Understanding, testing and managing model failures are the key focus of model risk management particularly model validation.
For machine learning models, particular attention is made on how to manage model fairness, explainability, robustness and change control. In this presentation, I will focus the discussion on machine learning explainability and robustness. Explainability is critical to evaluate conceptual soundness of models particularly for the applications in highly regulated institutions such as banks. There are many explainability tools available and my focus in this talk is how to develop fundamentally interpretable models.
Neural networks (including Deep Learning), with proper architectural choice, can be made to be highly interpretable models. Since models in production will be subjected to dynamically changing environments, testing and choosing robust models against changes are critical, an aspect that has been neglected in AutoML.
Scaling the mirrorworld with knowledge graphsAlan Morrison
After registration at https://www.brighttalk.com/webcast/9273/364148, you can view the full recording, which begins with Scott Abel's intro for a few minutes, then my talk for 20 minutes, and then Sebastian Gabler's. First presented on October 23 at an SWC webinar.
Conclusions:
(1) The mirrorworld (a world of digital twins, which will be 25 years in the making, according to Kevin Kelly) will require semantic knowledge graphs for interaction and interoperability.
(2) This fact implies massive future demand for knowledge graph technology and other new data infrastructure innovations, comparable to the scale of oil & gas industry infrastructure development over 150 years.
(3) Conceivably, knowledge graphs could be used to address a $205 billion market demand by 2021 for graph databases, information management, digital twins, conversational AI, virtual assistants and as knowledge bases/accelerated training for deep learning, etc. but the problem is that awareness of the tech is low, and the semantics community that understands the tech is still quite small.
(4) Over the next decades, knowledge graphs promise both scalability and substantial efficiencies in enterprises. But lack of awareness of its potential and how to harness it will continue to be stumbling blocks to adoption.
Algebraic machine learning (AML) is a relatively new machine learning technique based on algebraic representations of data. Unlike statistical learning, AML algorithms are robust regarding the statistical properties of the data and are parameter-free. The aim of the EU-funded ALMA project is to leverage AML properties to develop a new generation of interactive, human-centric machine learning systems. These systems are expected to reduce bias and prevent discrimination, remember what they know when they are taught something new, facilitate trust and reliability and integrate complex ethical constraints into human–artificial intelligence systems. Furthermore, they are expected to promote distributed, collaborative learning. More info at https://alma-ai.eu.
Full day lectures @International University, HCM City, Vietnam, May 2019. Review of AI in 2019; outlook into the future; empirical research in AI; introduction to AI research at Deakin University
Machine Learning has become a must to improve insight, quality and time to market. But it's also been called the 'high interest credit card of technical debt' with challenges in managing both how it's applied and how its results are consumed.
Machine learning with Big Data power point presentationDavid Raj Kanthi
This is an article made form the articles of IEEE published in the year 2017
The following presentation has the slides for the Title called the
Machine Learning with Big data. that following presentation which has the challenges and approaches of machine learning with big data.
The integration of the Big Data with Machine Learning has so many challenges that Big data has and what is the approach made by the machine learning mechanism for those challenges.
Computational Rationality I - a Lecture at Aalto University by Antti OulasvirtaAalto University
This 2-hour lecture looks at the emerging field of Computational Rationality. Lecture given March 12, 2018, for the Aalto University Master's level course on "Probabilistic Programming and Reinforcement Learning for Cognition and Interaction." Based on: Gershman et al 2015 Science, Lewis et al 2014 Topics in Cog Sci, and Gershman & Daw 2017 Annu Rev Psych
Deciphering AI - Unlocking the Black Box of AIML with State-of-the-Art Techno...Analytics India Magazine
Most organizations understand the predictive power and the potential gains from AIML, but AI and ML are still now a black box technology for them. While deep learning and neural networks can provide excellent inputs to businesses, leaders are challenged to use them because of the complete blind faith required to ‘trust’ AI. In this talk we will use the latest technological developments from researchers, the US defense department, and the industry to unbox the black box and provide businesses a clear understanding of the policy levers that they can pull, why, and by how much, to make effective decisions?
Why is image analytics Important? What good can come of caption generation or image descriptions? And how does Data Science & Machine learning techniques work on Image Analytics and to what purpose? We see how it works for the retail industry and for the Healthcare industry. What more? Take a look...
GRC 2020 - IIA - ISACA Machine Learning Monitoring, Compliance and GovernanceAndrew Clark
With Machine Learning (ML) taking on a more significant role in decision making, ML is becoming a risk management
and compliance issue. In light of increasing regulatory scrutiny, companies deploying ML must ensure that they have a
robust monitoring and compliance program. This presentation will provide context around relevant regulations, outline
critical risks and mitigating controls for ML, and provide an overview of monitoring and governance best practices.
This PPT Programming for data science in python mainly focus on importance of Python programming language in Python it explains the characteristic features of the programming language, its pros and cons and its applications.
machine learning in the age of big data: new approaches and business applicat...Armando Vieira
Presentation at University of Lisbon on Machine Learning and big data.
Deep learning algorithms and applications to credit risk analysis, churn detection and recommendation algorithms
As machine learning has is permeating more and more industries and businesses, the need for audit professionals to provide assurance over machine learning is growing. Andrew's presentation will provide an audit-centric overview of machine learning and present a framework for how to begin auditing machine learning in your organization.
QU Speaker Series - Session 3
https://qusummerschool.splashthat.com
A conversation with Quants, Thinkers and Innovators all challenged to innovate in turbulent times!
Join QuantUniversity for a complimentary summer speaker series where you will hear from Quants, innovators, startups and Fintech experts on various topics in Quant Investing, Machine Learning, Optimization, Fintech, AI etc.
Topic: Machine Learning and Model Risk (With a focus on Neural Network Models)
All models are wrong and when they are wrong they create financial or non-financial risks. Understanding, testing and managing model failures are the key focus of model risk management particularly model validation.
For machine learning models, particular attention is made on how to manage model fairness, explainability, robustness and change control. In this presentation, I will focus the discussion on machine learning explainability and robustness. Explainability is critical to evaluate conceptual soundness of models particularly for the applications in highly regulated institutions such as banks. There are many explainability tools available and my focus in this talk is how to develop fundamentally interpretable models.
Neural networks (including Deep Learning), with proper architectural choice, can be made to be highly interpretable models. Since models in production will be subjected to dynamically changing environments, testing and choosing robust models against changes are critical, an aspect that has been neglected in AutoML.
Scaling the mirrorworld with knowledge graphsAlan Morrison
After registration at https://www.brighttalk.com/webcast/9273/364148, you can view the full recording, which begins with Scott Abel's intro for a few minutes, then my talk for 20 minutes, and then Sebastian Gabler's. First presented on October 23 at an SWC webinar.
Conclusions:
(1) The mirrorworld (a world of digital twins, which will be 25 years in the making, according to Kevin Kelly) will require semantic knowledge graphs for interaction and interoperability.
(2) This fact implies massive future demand for knowledge graph technology and other new data infrastructure innovations, comparable to the scale of oil & gas industry infrastructure development over 150 years.
(3) Conceivably, knowledge graphs could be used to address a $205 billion market demand by 2021 for graph databases, information management, digital twins, conversational AI, virtual assistants and as knowledge bases/accelerated training for deep learning, etc. but the problem is that awareness of the tech is low, and the semantics community that understands the tech is still quite small.
(4) Over the next decades, knowledge graphs promise both scalability and substantial efficiencies in enterprises. But lack of awareness of its potential and how to harness it will continue to be stumbling blocks to adoption.
Algebraic machine learning (AML) is a relatively new machine learning technique based on algebraic representations of data. Unlike statistical learning, AML algorithms are robust regarding the statistical properties of the data and are parameter-free. The aim of the EU-funded ALMA project is to leverage AML properties to develop a new generation of interactive, human-centric machine learning systems. These systems are expected to reduce bias and prevent discrimination, remember what they know when they are taught something new, facilitate trust and reliability and integrate complex ethical constraints into human–artificial intelligence systems. Furthermore, they are expected to promote distributed, collaborative learning. More info at https://alma-ai.eu.
This presentation provides a comprehensive overview on ALMA, the EU-funded project aimed at leveraging AML properties to develop a new generation of interactive, human-centric machine learning systems.
The presentation provides a deep overview of the whole project, covering from the basics on Algebraic Machine Learning (AML) technology to the specifics of the ALMA project.
Call for Paper - International Conference on Machine Learning, NLP and Data M...ijgca
International Conference on Machine Learning, NLP and Data Mining (MLDA 2022)
will provide an excellent international forum for sharing knowledge and results in theory,
methodology and applications of Machine Learning, Natural Language Computing and Data
Mining. Authors are solicited to contribute to the conference by submitting articles that
illustrate research results, projects, surveying works and industrial experiences that describe
significant advances in the following areas, but are not limited to these topics only.
Workshop 1. Architecting Innovative Graph Applications
Join this hands-on workshop for beginners led by Neo4j experts guiding you to systematically uncover contextual intelligence. Using a real-life dataset we will build step-by-step a graph solution; from building the graph data model to running queries and data visualization. The approach will be applicable across multiple use cases and industries.
Call for Papers - International Conference on Machine Learning, NLP and Data ...IJNSA Journal
International Conference on Machine Learning, NLP and Data Mining (MLDA 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Machine Learning, Natural Language Computing and Data Mining. Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the following areas, but are not limited to these topics only.
Call for Paper - International Conference on Machine Learning, NLP and Data M...ijgca
International Conference on Machine Learning, NLP and Data Mining (MLDA 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Machine Learning, Natural Language Computing and Data Mining. Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the following areas, but are not limited to these topics only.
From DevOps to MLOps: practical steps for a smooth transitionAnne-Marie Tousch
Abstract: There has been tremendous progress in artificial intelligence recently. There's no doubt one day it will also power Datadog products and you'll have to deal with it in your pipelines. What is it going to change? In this talk, I'll explain what makes ML fundamentally different than software engineering, and present a few of the operational challenges of setting up a machine learning system in the real world. Most importantly, I’ll propose practical steps to prepare the transition, that do not require you having a machine model running yet.
This talk was given at a Ladies of Code Meetup in Paris, in May 2023.
Recording: https://www.youtube.com/watch?v=S9l8GO4wtdY
Meetup: https://www.meetup.com/fr-FR/ladies-of-code-paris/events/293711765/
In Drazen talk, you will get a chance to listen to how Data Science Master 4.0 on Belgrade University was created, and what are the benefits of the program.
[RecSys2023] Challenging the Myth of Graph Collaborative Filtering: a Reasone...Daniele Malitesta
Slides for the paper "Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis", accepted and presented at the 17th ACM Conference on Recommender Systems (RecSys'23).
Paper: https://dl.acm.org/doi/10.1145/3604915.3609489
Code: https://github.com/sisinflab/Graph-RSs-Reproducibility
Call for Paper - International Conference on Machine Learning, NLP and Data M...mlaij
International Conference on Machine Learning, NLP and Data Mining (MLDA 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Machine Learning, Natural Language Computing and Data Mining. Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the following areas, but are not limited to these topics only.
OpenACC and Open Hackathons Monthly Highlights June 2022.pdfOpenACC
Stay up-to-date with the OpenACC and Open Hackathons Monthly Highlights. June’s edition covers the 2022 OpenACC and Hackathons Summit, NSF’s Traineeship Program, NVIDIA’s Academic Hardware Grant program, upcoming Open Hackathons and Bootcamps, recent research, new resources, and more!
A apresentação será conduzida por Leonardo Mauro P. Moraes, Team Leader pela Amaris Consulting e Doutorando em Inteligência Artificial pela Universidade de São Paulo. 🎓
O Machine Learning é uma tecnologia muito utilizada na área de #datascience faz alguns anos, porém como implementar e manter esse conceito de uma forma confiável e eficaz? O Machine Learning Operations (#mlops) procura responder esta pergunta utilizando-se de engenharia de software e de dados, assim criando um ciclo de vida, em respeito à modelagem, implementação, monitoramento, distribuição, e escalabilidade de Machine Learning, fazendo a ponte entre o desenvolvimento e a operação do modelo.
Gravação: https://www.youtube.com/live/iwmaEABBeYw?si=R_YujavuSxec8MtF&t=265
Call for Papers - International Conference on Machine Learning, NLP and Data ...dannyijwest
nternational Conference on Machine Learning, NLP and Data Mining (MLDA 2022)
will provide an excellent international forum for sharing knowledge and results in theory,
methodology and applications of Machine Learning, Natural Language Computing and Data
Mining. Authors are solicited to contribute to the conference by submitting articles that
illustrate research results, projects, surveying works and industrial experiences that describe
significant advances in the following areas, but are not limited to these topics only.
IC-SDV 2018: Aleksandar Kapisoda (Boehringer) Using Machine Learning for Auto...Dr. Haxel Consult
Focusing on the significance of targets is one of the key drivers for quality of web search.
Filtering targeted companies based on the significance of their business model for the expected search results was one of our “nice to haves” last year.
Evaluating a number of artificial intelligence approaches based on neural networks, classical machine learning and semantic technologies lead us to a working hybrid approach.
It's MY JOB: Identifying and Improving Content Quality for Online recruitmen...IIIT Hyderabad
Online recruitment platforms such as LinkedIn, Glassdoor, Indeed.com, and naukri.com are used to build business connections, find jobs, and recruit Candidates. These platforms increase recruiter productivity, help reach wider audiences, and provide a rich source of information for job seekers. These platforms also witness enormous volumes of user-generated content such as job postings, CVs, and company profiles. Among this content, job postings are important for identifying, analyzing, and determining the roles, responsibilities and skills of a specific position.
These act as a gateway for job seekers to understand the requirement and help the recruiter attract the right talent. But some of these contain untenable facts, vague, non-standard, and missing entities that dilute the content quality over the platforms. The unmonitored nature of this content makes it difficult to assess the information's credibility, affecting the platform's trustworthiness and, in turn, the user experience. Therefore, there is a need to identify, analyze, and enhance the content quality on these platforms. In this report, we look at different perspectives, literature, and work done for content quality analysis, detection and enhancement over online recruitment platforms.
Learn about the accomplishments and activities of the OpenACC organization over the course of 2019. This OpenACC Highlights covers the newest additions to the OpenACC leadership, the updated specification, conference participation, GPU Hackathons and more.
International Conference on NLP, Data Mining and Machine Learning (NLDML 2022)kevig
International Conference on NLP, Data Mining and Machine Learning (NLDML 2022)
will provide an excellent international forum for sharing knowledge and results in theory,
methodology and applications of Natural Language Computing, Data Mining and Machine
Learning.
It will provide an excellent international forum for sharing knowledge and results in theory,
methodology and applications of Natural Language Computing, Data Mining and Machine
Learning. The Conference looks for significant contributions to all major fields of the Natural
Language Computing, Data Mining and Machine Learning in theoretical and practical
aspects.
Similar to Introduction to Machine Learning, Hands-on Deep Learning with Tensroflow 2.0 (20)
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Subhajit Sahu
Abstract — Levelwise PageRank is an alternative method of PageRank computation which decomposes the input graph into a directed acyclic block-graph of strongly connected components, and processes them in topological order, one level at a time. This enables calculation for ranks in a distributed fashion without per-iteration communication, unlike the standard method where all vertices are processed in each iteration. It however comes with a precondition of the absence of dead ends in the input graph. Here, the native non-distributed performance of Levelwise PageRank was compared against Monolithic PageRank on a CPU as well as a GPU. To ensure a fair comparison, Monolithic PageRank was also performed on a graph where vertices were split by components. Results indicate that Levelwise PageRank is about as fast as Monolithic PageRank on the CPU, but quite a bit slower on the GPU. Slowdown on the GPU is likely caused by a large submission of small workloads, and expected to be non-issue when the computation is performed on massive graphs.
Show drafts
volume_up
Empowering the Data Analytics Ecosystem: A Laser Focus on Value
The data analytics ecosystem thrives when every component functions at its peak, unlocking the true potential of data. Here's a laser focus on key areas for an empowered ecosystem:
1. Democratize Access, Not Data:
Granular Access Controls: Provide users with self-service tools tailored to their specific needs, preventing data overload and misuse.
Data Catalogs: Implement robust data catalogs for easy discovery and understanding of available data sources.
2. Foster Collaboration with Clear Roles:
Data Mesh Architecture: Break down data silos by creating a distributed data ownership model with clear ownership and responsibilities.
Collaborative Workspaces: Utilize interactive platforms where data scientists, analysts, and domain experts can work seamlessly together.
3. Leverage Advanced Analytics Strategically:
AI-powered Automation: Automate repetitive tasks like data cleaning and feature engineering, freeing up data talent for higher-level analysis.
Right-Tool Selection: Strategically choose the most effective advanced analytics techniques (e.g., AI, ML) based on specific business problems.
4. Prioritize Data Quality with Automation:
Automated Data Validation: Implement automated data quality checks to identify and rectify errors at the source, minimizing downstream issues.
Data Lineage Tracking: Track the flow of data throughout the ecosystem, ensuring transparency and facilitating root cause analysis for errors.
5. Cultivate a Data-Driven Mindset:
Metrics-Driven Performance Management: Align KPIs and performance metrics with data-driven insights to ensure actionable decision making.
Data Storytelling Workshops: Equip stakeholders with the skills to translate complex data findings into compelling narratives that drive action.
Benefits of a Precise Ecosystem:
Sharpened Focus: Precise access and clear roles ensure everyone works with the most relevant data, maximizing efficiency.
Actionable Insights: Strategic analytics and automated quality checks lead to more reliable and actionable data insights.
Continuous Improvement: Data-driven performance management fosters a culture of learning and continuous improvement.
Sustainable Growth: Empowered by data, organizations can make informed decisions to drive sustainable growth and innovation.
By focusing on these precise actions, organizations can create an empowered data analytics ecosystem that delivers real value by driving data-driven decisions and maximizing the return on their data investment.
StarCompliance is a leading firm specializing in the recovery of stolen cryptocurrency. Our comprehensive services are designed to assist individuals and organizations in navigating the complex process of fraud reporting, investigation, and fund recovery. We combine cutting-edge technology with expert legal support to provide a robust solution for victims of crypto theft.
Our Services Include:
Reporting to Tracking Authorities:
We immediately notify all relevant centralized exchanges (CEX), decentralized exchanges (DEX), and wallet providers about the stolen cryptocurrency. This ensures that the stolen assets are flagged as scam transactions, making it impossible for the thief to use them.
Assistance with Filing Police Reports:
We guide you through the process of filing a valid police report. Our support team provides detailed instructions on which police department to contact and helps you complete the necessary paperwork within the critical 72-hour window.
Launching the Refund Process:
Our team of experienced lawyers can initiate lawsuits on your behalf and represent you in various jurisdictions around the world. They work diligently to recover your stolen funds and ensure that justice is served.
At StarCompliance, we understand the urgency and stress involved in dealing with cryptocurrency theft. Our dedicated team works quickly and efficiently to provide you with the support and expertise needed to recover your assets. Trust us to be your partner in navigating the complexities of the crypto world and safeguarding your investments.
Explore our comprehensive data analysis project presentation on predicting product ad campaign performance. Learn how data-driven insights can optimize your marketing strategies and enhance campaign effectiveness. Perfect for professionals and students looking to understand the power of data analysis in advertising. for more details visit: https://bostoninstituteofanalytics.org/data-science-and-artificial-intelligence/
Opendatabay - Open Data Marketplace.pptxOpendatabay
Opendatabay.com unlocks the power of data for everyone. Open Data Marketplace fosters a collaborative hub for data enthusiasts to explore, share, and contribute to a vast collection of datasets.
First ever open hub for data enthusiasts to collaborate and innovate. A platform to explore, share, and contribute to a vast collection of datasets. Through robust quality control and innovative technologies like blockchain verification, opendatabay ensures the authenticity and reliability of datasets, empowering users to make data-driven decisions with confidence. Leverage cutting-edge AI technologies to enhance the data exploration, analysis, and discovery experience.
From intelligent search and recommendations to automated data productisation and quotation, Opendatabay AI-driven features streamline the data workflow. Finding the data you need shouldn't be a complex. Opendatabay simplifies the data acquisition process with an intuitive interface and robust search tools. Effortlessly explore, discover, and access the data you need, allowing you to focus on extracting valuable insights. Opendatabay breaks new ground with a dedicated, AI-generated, synthetic datasets.
Leverage these privacy-preserving datasets for training and testing AI models without compromising sensitive information. Opendatabay prioritizes transparency by providing detailed metadata, provenance information, and usage guidelines for each dataset, ensuring users have a comprehensive understanding of the data they're working with. By leveraging a powerful combination of distributed ledger technology and rigorous third-party audits Opendatabay ensures the authenticity and reliability of every dataset. Security is at the core of Opendatabay. Marketplace implements stringent security measures, including encryption, access controls, and regular vulnerability assessments, to safeguard your data and protect your privacy.
2. scientia potentia est
GDG Baku 2019 - Natig Vahabov 2
“Knowledge is power”
Sir Francis Bacon, 16th century
English philosopher
3. Agenda
• AI & ML & DL
• Theory of CNN
• Hands on Tensorflow 2.0
• Building CNN with Keras
• Django + Tensorflow (trained model)
GDG Baku 2019 - Natig Vahabov 3
6. What is AI?
Academic term:
As the study of "intelligent agents": any device that
perceives its environment and takes actions that
maximize its chance of successfully achieving its
goals
Simple term:
A.I. is the study of how to make computers do
things at which, at the moment, people are better.
GDG Baku 2019 - Natig Vahabov 6
7. Weak AI vs Strong AI
Weak or Narrow AI is a type of artificial intelligence that
is focused on one narrow task
- Siri, Alexa, Sophia
On the other hand, Artificial General Intelligence (AGI) is
the intelligence of an intelligent agent that can
understand or learn any intellectual task that
a human being can (Strong AI)
- Samantha (‘Her’ movie)
GDG Baku 2019 - Natig Vahabov 7
8. Good, Old-Fashioned AI(GOFAI)
The Intelligent Agent must inertly duplicate the
human mind in a such manner that the
synthetic mind
• can be studied
• can be animated within the memory of the
Intelligent Agent
GDG Baku 2019 - Natig Vahabov 8
9. Expert System as GOFAI
‘An expert system is a computer system
that emulates, or acts in all respects, with
the decision-making capabilities of a human
expert’.
Prof Edward Feigenbaum
GDG Baku 2019 - Natig Vahabov 9
11. MYCIN
Diagnosing and treating patients with infectious blood
diseases
• a rule-based expert system
• developed at Stanford University – 1976
• uses backward chaining for reasoning
• incorporates about 500 rules
• written in INTERLISP (a dialect of LISP)
• a correct diagnosis rate of about 65% even though it
was worse than real physicians who had average
correct diagnosis rates of about 80%
GDG Baku 2019 - Natig Vahabov 11
12. Machine Learning
Machine Learning is the field of study that gives
computers the ability to learn without being
explicitly programmed.
Arthur Samuel, 1959
GDG Baku 2019 - Natig Vahabov 12
13. Machine Learning
A computer program is said to learn from
experience E with respect to some task T and some
performance measure P, if its performance on T, as
measured by P, improves with experience E
Tom Mitchell, 1997
GDG Baku 2019 - Natig Vahabov 13
14. Blood Disorder with ML
University of Colorado, Nov 6th 2019
GDG Baku 2019 - Natig Vahabov 14
16. Machine Learning vs ES
Task: Spam/ Ham detection(T) (Supervised
Learning, Classification problem)
• ES – writing rules (with knowledge
representation - FirstOrderLogic) which
classifies an email as a spam
• ML – give previous spam/ham emails(E), train
the model, evaluate the solution(P), analyze
errors, update the model weights
GDG Baku 2019 - Natig Vahabov 16
17. Machine Learning vs ES
Machine Learning is great for:
• Problems for which existing solutions require a lot of hand-
tuning or long lists of rules: one Machine Learning algorithm can
often simplify code and perform better.
• Complex problems for which there is no good solution at all
using a traditional approach: the best Machine Learning
techniques can find a solution.
• Fluctuating environments: a Machine Learning system can adapt
to new data.
• Getting insights about complex problems and large amounts of
data.
GDG Baku 2019 - Natig Vahabov 17
19. Machine Learning Systems
• Whether or not they are trained with human
supervision (supervised, unsupervised, semi-
supervised, and Reinforcement Learning)
• Whether or not they can learn incrementally on the fly
(online versus batch learning)
• Whether they work by simply comparing new data
points to known data points, or instead detect
patterns in the training data and build a predictive
model, much like scientists do (instance-based
versus model-based learning)
GDG Baku 2019 - Natig Vahabov 19
20. Supervised MLSs
• In supervised learning, the training data you feed to
the algorithm includes the desired solutions, called
labels
• Two main categories: Regression and Classification
• Main Algorithms:
– k-Nearest Neighbors (recommender system, similar users)
– Linear Regression (house price prediction)
– Logistic Regression (spam/ham filter)
– Support Vector Machines (face detection)
– Decision Trees and Random Forests (google photos)
– Neural networks
GDG Baku 2019 - Natig Vahabov 20
22. Logistic Regression in practice
• Political campaigns try to
predict the chances that a
voter will vote for their
candidate
• Bankers use it to predict
the chances that a loan
applicant will default on the
loan
• Marketers use it to predict
whether a customer will
respond to a particular ad
GDG Baku 2019 - Natig Vahabov 22
23. Unsupervised MLSs
• In unsupervised learning, the training data is unlabeled
• Clustering
– K-Means, DBSCAN, Hierarchical Cluster Analysis (HCA)
• Anomaly detection and novelty detection
– One-class SVM, Isolation Forest
• Visualization and dimensionality reduction
– Principal Component Analysis (PCA), Kernel PCA
– Locally-Linear Embedding (LLE)
– t-distributed Stochastic Neighbor Embedding (t-SNE)
• Association rule learning
– Apriori
– Eclat
GDG Baku 2019 - Natig Vahabov 23
24. Apriori in practice
Wal-Mart actually used the Apriori
algorithm to increase sales of
beer. Wal-Mart studied their data
to find that American males who
bought diapers on Friday
afternoons also frequently bought
beer. They moved the beer next to
the diapers, and sales increased
(Tesco in UK did the same)
GDG Baku 2019 - Natig Vahabov 24
25. Semi-supervised MLSs
• Some algorithms can deal with partially labeled
training data, usually a lot of unlabeled data and a
little bit of labeled data. This is called semisupervised
learning
• Google Photos (detecting faces, assigns them to a
person)
• Webpage classification (news, educational, shopping,
blog ..)
GDG Baku 2019 - Natig Vahabov 25
27. Reinforcement Learning
• The Man vs. The Machine / Deep Blue defeated Garry
Kasparov in 1997
• At the 2017 Future of Go Summit, DeepMind’s
successor AlphaGo Master beat Ke Jie, the world No.1
ranked player at the time, in a three-game match
• Robotics that mimics real animals
• Alibaba Group published a paper “Real-Time Bidding
with Multi-Agent Reinforcement Learning in Display
Advertising”
GDG Baku 2019 - Natig Vahabov 27
28. What exactly does a
machine learning
engineer do?
GDG Baku 2019 - Natig Vahabov 28
29. Machine Learning Engineer
• Running machine learning experiments using a
programming language with machine learning
libraries.
• Deploying machine learning solutions into
production.
• Optimizing solutions for performance and scalability.
• Data engineering, i.e. ensuring a good data flow
between database and backend systems.
• Implementing custom machine learning code.
• Data science, i.e. analyzing data and coming up with
use cases
GDG Baku 2019 - Natig Vahabov 29
34. If ML solves our problem,
why do we need DL?
GDG Baku 2019 - Natig Vahabov 34
35. Reason1: Massive Data
Amount of data that are generated in a single day of
2019
• 500 million tweets are sent
• 294 billion emails are sent
• 4 petabytes of data are created on Facebook
• 4 terabytes of data are created from each connected car
• 65 billion messages are sent on WhatsApp
• 5 billion searches are made
• By 2025, it’s estimated that 463 exabytes of data will be created
each day globally – that’s the equivalent of 212,765,957 DVDs per
day!
GDG Baku 2019 - Natig Vahabov 35
37. Reason2: Moore’s Law
Moore's law is the observation that the
number of transistors in a dense
integrated circuit doubles about every 18-
24 months
TPU >> GPU >> CPU
GDG Baku 2019 - Natig Vahabov 37
45. Why we should use framework?
• High level abstracted API
• Code friendly environment with engineers
• Easy hands-on adaptation with newbies
• Advance visualization of inside NN
(Tensorboard)
• Single tool for both development and serving
(TFServing)
• Option to run of recent academic papers
(paperswithcode.com)
GDG Baku 2019 - Natig Vahabov 45
46. Bones of DLF
• Components of any DL framework
– Tensors
– Operations
– Computation Graph
– Auto-differentiation
– Fast and Efficient floating pt. Operations
– GPU support
• BLAS, cuBLAS, cuDNN
GDG Baku 2019 - Natig Vahabov 46
47. Tensorflow
Google’s Tensorflow — arguably the most popular
Deep Learning framework today. Gmail, Uber,
Airbnb, Nvidia and lots of other prominent brands
using it.
• Python is the most convenient client language for
working with TensorFlow. However, there are also
experimental interfaces available in JavaScript, C
++, Java and Go, C # and Julia
• Ability to run models on mobile platforms like iOS
and Android
• TF needs a lot of coding
• TF operates with a static computation graph
GDG Baku 2019- Natig Vahabov 47
48. Keras
It’s the most minimalist approach to using
TensorFlow, Theano, or CNTK in the high-level
• Creating massive models of deep learning in
Keras is reduced to single-line functions. But this
strategy makes Keras a less configurable
environment than low-level frameworks
• Keras model Serialization/Deserialization APIs,
callbacks, and data streaming using Python
generators are very mature
• Keras results in a much more readable and
succinct code
GDG Baku 2019- Natig Vahabov 48
49. PyTorch
The PyTorch framework was developed for Facebook
services but is already used for its own tasks by
companies like Twitter and Salesforce.
• Unlike TensorFlow, the PyTorch library operates
with a dynamically updated graph. This means that
it allows you to make changes to the architecture
in the process
• In PyTorch, standard debuggers, for example, pdb
or PyCharm can be used
• PyTorch is much better suited for small projects
and prototyping. When it comes to cross-platform
solutions, TensorFlow looks like a more suitable
choice
GDG Baku 2019- Natig Vahabov 49
50. Caffe2
Caffe supports many different types of deep learning
architectures geared towards image
classification and image segmentation such as CNN,
RCNN, LSTM and fully connected neural network
designs
• Caffe is being used in academic research projects,
startup prototypes, and even large-scale
industrial applications in vision, speech, and
multimedia
• Yahoo! has also integrated caffe with Apache
Spark to create CaffeOnSpark, a distributed deep
learning framework
• At the end of March 2018, Caffe2 was merged
into PyTorch
GDG Baku 2019- Natig Vahabov 50
51. Sonnet
Sonnet deep learning framework built on top of
TensorFlow. It is designed to create neural networks
with a complex architecture by the world famous
company DeepMind.
• High-level object-oriented libraries that bring
about abstraction when developing neural
networks (NN) or other machine learning (ML)
algorithms
• The main advantage of Sonnet, is you can use it
to reproduce the research demonstrated in
DeepMind’s papers with greater ease than Keras,
since DeepMind will be using Sonnet themselves
GDG Baku 2019- Natig Vahabov 51
52. MXNet
MXNet, as an Apache product, is very effective
framework for parallel on multiple GPUs and many
machines. This, in particular, has been demonstrated
by his work on Amazon Web Services
• The framework initially supports a large number
of languages (C ++, Python, R, Julia, JavaScript,
Scala, Go, and even Perl)
• Support of multiple GPUs (with optimized
computations and fast context switching)
• Fast problem-solving ability
GDG Baku 2019- Natig Vahabov 52
53. Gluon
the Gluon supports work with a dynamic graph,
combining this with high-performance MXNet. From
this perspective, Gluon looks like an extremely
interesting alternative to Keras for distributed
computing
• Gluon is based on MXNet and offers a simple API
that simplifies the creation of deep learning
models
• Gluon enables to define neural network models
that are dynamic, meaning they can be built on
the fly, with any structure, and using any of
Python’s native control flow
GDG Baku 2019- Natig Vahabov 53
54. CNTK
CNTK is one of the most widely known machine
learning frameworks in the market, which is
developed by Microsoft that features great
compatibility and effective use of computational
resources
• Microsoft Cognitive Toolkit (previously CNTK) is
a deep learning framework developed
by Microsoft Research
• CNTK support for CUDA 10
• CNTK contributes to ONNX development and
runtime.
GDG Baku 2019- Natig Vahabov 54
55. Chainer
Until the advent of DyNet at CMU, and PyTorch at
Facebook, Chainer was the leading neural network
framework for dynamic computation graphs or nets
that allowed for input of varying length, a popular
feature for NLP tasks.
• Chainer is the first framework to use a dynamic
architecture model
• Better GPU & GPU data center performance than
TensorFlow. Recently, Chainer became the world
champion for GPU data center performance
• OOP like programming style
GDG Baku 2019- Natig Vahabov 55
56. DL4J
Those who are on a short leg with Java or Scala
should pay attention to DL4J
• The process is supported by Hadoop and
Spark architectures
• Using Java allows you to use the library in the
development cycle of programs for Android
devices
• Training of neural networks in DL4J is carried out
in parallel through iterations through clusters
GDG Baku 2019- Natig Vahabov 56
57. ONNX
The ONNX project was born from the collaboration
of Microsoft and Facebook as a search for an open
format for the presentation of deep learning models.
ONNX simplifies the process of transferring models
between different means of working with artificial
intelligence
• ONNX enables models to be trained in one
framework and transferred to another for
inference. ONNX models are currently supported
in Caffe2, Microsoft Cognitive Toolkit, MXNet, and
PyTorch, and there are connectors for many other
common frameworks and libraries
GDG Baku 2019- Natig Vahabov 57
58. Which DLF Should You Use
• If you are just starting out and want to figure out
what’s what, the best choice is Keras
• For research purposes, choose PyTorch
• For production, you need to focus on the
environment. So, for Google Cloud, the best choice
is TensorFlow, for AWS — MXNet and Gluon.
• Android developers should pay attention to D4LJ, for
iOS, a similar range of tasks is compromised by Core
ML.
• Finally, ONNX will help with questions of interaction
between different frameworks.
GDG Baku 2019 - Natig Vahabov 58
62. ConvNet
• CNN is a class of deep neural networks, most
commonly applied to analyzing visual imagery
• Layers:
– Convolution layer + ReLu layer
– Pooling layer
– Flattening layer
– Full Connection layer
• Applications:
– Image and video recognition
– Recommender systems
– Image classification, medical image analysis
– Natural language processing
GDG Baku 2019- Natig Vahabov 62
63. Fashion MNIST
It is a dataset comprised of 60,000
small square 28×28 pixel grayscale
images of items of 10 types of clothing,
such as:
0: T-shirt/top
1: Trouser
2: Pullover
3: Dress
4: Coat
5: Sandal
6: Shirt
7: Sneaker
8: Bag
9: Ankle boot
GDG Baku 2019- Natig Vahabov 63
85. Machine Learning Video Courses
• Coursera — Machine Learning (Andrew Ng)
• Coursera — Neural Networks for Machine Learning (Geoffrey Hinton)
• Udacity — Intro to Machine Learning (Sebastian Thrun)
• Udacity — Machine Learning (Georgia Tech)
• Udacity — Deep Learning (Vincent Vanhoucke)
• Machine Learning (mathematicalmonk)
• Practical Deep Learning For Coders (Jeremy Howard & Rachel Thomas)
• Stanford CS231n — Convolutional Neural Networks for Visual
Recognition (Winter 2016) (class link)
• Stanford CS224n — Natural Language Processing with Deep Learning
(Winter 2017) (class link)
• Oxford Deep NLP 2017 (Phil Blunsom et al.)
• Reinforcement Learning (David Silver)
• Practical Machine Learning Tutorial with Python (sentdex)
GDG Baku 2019 - Natig Vahabov 85
86. Machine Learning Blogs
• Andrej Karpathy
• i am trask
• Christopher Olah
• Top Bots
• WildML
• Distill
• Machine Learning Mastery
• FastML
• Adventures in NI
• Sebastian Ruder
• Unsupervised Methods
• Explosion
• Tim Dettmers
• When trees fall…
• ML@B
GDG Baku 2019 - Natig Vahabov 86
87. Machine Learning Theory
• Machine Learning, Stanford University
• Machine Learning, Carnegie Mellon University
• Machine Learning, MIT
• Machine Learning, California Institute of
Technology
• Machine Learning, Oxford University
• Machine Learning, Data School
GDG Baku 2019 - Natig Vahabov 87
88. Deep Learning Theory
• Deep Learning, Ian Goodfellow
• Neural Networks and Deep Learning
• Understanding LSTM Networks
• Deep Residual Learning
GDG Baku 2019 - Natig Vahabov 88