The document provides an overview of machine learning concepts including linear regression, artificial neural networks, and convolutional neural networks. It discusses how artificial neural networks are inspired by biological neurons and can learn relationships in data. The document uses the MNIST dataset example to demonstrate how a neural network can be trained to classify images of handwritten digits using backpropagation to adjust weights to minimize error. TensorFlow is introduced as a popular Python library for building machine learning models, enabling flexible creation and training of neural networks.
Machine Learning Essentials Demystified part1 | Big Data DemystifiedOmid Vahdaty
Machine Learning Essentials Abstract:
Machine Learning (ML) is one of the hottest topics in the IT world today. But what is it really all about?
In this session we will talk about what ML actually is and in which cases it is useful.
We will talk about a few common algorithms for creating ML models and demonstrate their use with Python. We will also take a peek at Deep Learning (DL) and Artificial Neural Networks and explain how they work (without too much math) and demonstrate DL model with Python.
The target audience are developers, data engineers and DBAs that do not have prior experience with ML and want to know how it actually works.
Presentation in Vietnam Japan AI Community in 2019-05-26.
The presentation summarizes what I've learned about Regularization in Deep Learning.
Disclaimer: The presentation is given in a community event, so it wasn't thoroughly reviewed or revised.
Deep Learning in Recommender Systems - RecSys Summer School 2017Balázs Hidasi
This is the presentation accompanying my tutorial about deep learning methods in the recommender systems domain. The tutorial consists of a brief general overview of deep learning and the introduction of the four most prominent research direction of DL in recsys as of 2017. Presented during RecSys Summer School 2017 in Bolzano, Italy.
Artificial Neural Networks have been very successfully used in several machine learning applications. They are often the building blocks when building deep learning systems. We discuss the hypothesis, training with backpropagation, update methods, regularization techniques.
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017MLconf
Corinna Cortes is a Danish computer scientist known for her contributions to machine learning. She is currently the Head of Google Research, New York. Cortes is a recipient of the Paris Kanellakis Theory and Practice Award for her work on theoretical foundations of support vector machines.
Cortes received her M.S. degree in physics from Copenhagen University in 1989. In the same year she joined AT&T Bell Labs as a researcher and remained there for about ten years. She received her Ph.D. in computer science from the University of Rochester in 1993. Cortes currently serves as the Head of Google Research, New York. She is an Editorial Board member of the journal Machine Learning.
Cortes’ research covers a wide range of topics in machine learning, including support vector machines and data mining. In 2008, she jointly with Vladimir Vapnik received the Paris Kanellakis Theory and Practice Award for the development of a highly effective algorithm for supervised learning known as support vector machines (SVM). Today, SVM is one of the most frequently used algorithms in machine learning, which is used in many practical applications, including medical diagnosis and weather forecasting.
Abstract Summary:
Harnessing Neural Networks:
Deep learning has demonstrated impressive performance gain in many machine learning applications. However, unveiling and realizing these performance gains is not always straightforward. Discovering the right network architecture is critical for accuracy and often requires a human in the loop. Some network architectures occasionally produce spurious outputs, and the outputs have to be restricted to meet the needs of an application. Finally, realizing the performance gain in a production system can be difficult because of extensive inference times.
In this talk we discuss methods for making neural networks efficient in production systems. We also discuss an efficient method for automatically learning the network architecture, called AdaNet. We provide theoretical arguments for the algorithm and present experimental evidence for its effectiveness.
Discusses the concept of Language Models in Natural Language Processing. The n-gram models, markov chains are discussed. Smoothing techniques such as add-1 smoothing, interpolation and discounting methods are addressed.
Machine Learning Essentials Demystified part1 | Big Data DemystifiedOmid Vahdaty
Machine Learning Essentials Abstract:
Machine Learning (ML) is one of the hottest topics in the IT world today. But what is it really all about?
In this session we will talk about what ML actually is and in which cases it is useful.
We will talk about a few common algorithms for creating ML models and demonstrate their use with Python. We will also take a peek at Deep Learning (DL) and Artificial Neural Networks and explain how they work (without too much math) and demonstrate DL model with Python.
The target audience are developers, data engineers and DBAs that do not have prior experience with ML and want to know how it actually works.
Presentation in Vietnam Japan AI Community in 2019-05-26.
The presentation summarizes what I've learned about Regularization in Deep Learning.
Disclaimer: The presentation is given in a community event, so it wasn't thoroughly reviewed or revised.
Deep Learning in Recommender Systems - RecSys Summer School 2017Balázs Hidasi
This is the presentation accompanying my tutorial about deep learning methods in the recommender systems domain. The tutorial consists of a brief general overview of deep learning and the introduction of the four most prominent research direction of DL in recsys as of 2017. Presented during RecSys Summer School 2017 in Bolzano, Italy.
Artificial Neural Networks have been very successfully used in several machine learning applications. They are often the building blocks when building deep learning systems. We discuss the hypothesis, training with backpropagation, update methods, regularization techniques.
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017MLconf
Corinna Cortes is a Danish computer scientist known for her contributions to machine learning. She is currently the Head of Google Research, New York. Cortes is a recipient of the Paris Kanellakis Theory and Practice Award for her work on theoretical foundations of support vector machines.
Cortes received her M.S. degree in physics from Copenhagen University in 1989. In the same year she joined AT&T Bell Labs as a researcher and remained there for about ten years. She received her Ph.D. in computer science from the University of Rochester in 1993. Cortes currently serves as the Head of Google Research, New York. She is an Editorial Board member of the journal Machine Learning.
Cortes’ research covers a wide range of topics in machine learning, including support vector machines and data mining. In 2008, she jointly with Vladimir Vapnik received the Paris Kanellakis Theory and Practice Award for the development of a highly effective algorithm for supervised learning known as support vector machines (SVM). Today, SVM is one of the most frequently used algorithms in machine learning, which is used in many practical applications, including medical diagnosis and weather forecasting.
Abstract Summary:
Harnessing Neural Networks:
Deep learning has demonstrated impressive performance gain in many machine learning applications. However, unveiling and realizing these performance gains is not always straightforward. Discovering the right network architecture is critical for accuracy and often requires a human in the loop. Some network architectures occasionally produce spurious outputs, and the outputs have to be restricted to meet the needs of an application. Finally, realizing the performance gain in a production system can be difficult because of extensive inference times.
In this talk we discuss methods for making neural networks efficient in production systems. We also discuss an efficient method for automatically learning the network architecture, called AdaNet. We provide theoretical arguments for the algorithm and present experimental evidence for its effectiveness.
Discusses the concept of Language Models in Natural Language Processing. The n-gram models, markov chains are discussed. Smoothing techniques such as add-1 smoothing, interpolation and discounting methods are addressed.
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8Hakky St
This is the documentation of the study-meeting in lab.
Tha book title is "Hands-On Machine Learning with Scikit-Learn and TensorFlow" and this is the chapter 8.
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...Balázs Hidasi
Slides for my RecSys 2016 talk on integrating image and textual information into session based recommendations using novel parallel RNN architectures.
Link to the paper: http://www.hidasi.eu/en/publications.html#p_rnn_recsys16
This presentation is a part of ML Course and this deals with some of the basic concepts such as different types of learning, definitions of classification and regression, decision surfaces etc. This slide set also outlines the Perceptron Learning algorithm as a starter to other complex models to follow in the rest of the course.
Artificial Intelligence, Machine Learning and Deep LearningSujit Pal
Slides for talk Abhishek Sharma and I gave at the Gennovation tech talks (https://gennovationtalks.com/) at Genesis. The talk was part of outreach for the Deep Learning Enthusiasts meetup group at San Francisco. My part of the talk is covered from slides 19-34.
Generative Adversarial Networks : Basic architecture and variantsananth
In this presentation we review the fundamentals behind GANs and look at different variants. We quickly review the theory such as the cost functions, training procedure, challenges and go on to look at variants such as CycleGAN, SAGAN etc.
발표자: 곽동현(서울대 박사과정, 현 NAVER Clova)
강화학습(Reinforcement learning)의 개요 및 최근 Deep learning 기반의 RL 트렌드를 소개합니다.
발표영상:
http://tv.naver.com/v/2024376
https://youtu.be/dw0sHzE1oAc
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...Balázs Hidasi
Slides of my presentation at CIKM2018 about version 2 of the GRU4Rec algorithm, a recurrent neural network based algorithm for the session-based recommendation task.
We discuss sampling strategies and introduce additional sampling to the algorithm. We also redesign the loss function to cope with additional sampling. The resulting BPR-max loss function is able to efficiently handle many negative samples without encountering the vanishing gradient problem. We also introduce constrained embeddings which speeds up the conversion of item representations and reduces memory usage by a factor of 4. These improvements increase offline measures up to 52%.
In the talk we also discuss online A/B test and the implications of long time observations. Most of these observations are exclusive to this talk and are not in the paper.
You can access the preprint version of the paper on arXiv: https://arxiv.org/abs/1706.03847
The code is available on GitHub: https://github.com/hidasib/GRU4Rec
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14Daniel Lewis
Piotr Mirowski (of Microsoft Bing London) presented Review of Auto-Encoders to the Computational Intelligence Unconference 2014, with our Deep Learning stream. These are his slides. Original link here: https://piotrmirowski.files.wordpress.com/2014/08/piotrmirowski_ciunconf_2014_reviewautoencoders.pptx
He also has Matlab-based tutorial on auto-encoders available here:
https://github.com/piotrmirowski/Tutorial_AutoEncoders/
Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTECBAINIDA
Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC
คณะสถิติประยุกต์ สถาบันบัณฑิตพัฒนบริหารศาสตร์ ร่วมกับ Data Science Thailand ร่วมกันจัดงาน The First NIDA Business Analytics and Data Sciences Contest/Conference
Machine learning the next revolution or just another hypeJorge Ferrer
These are the slides of my session and ModConf / Liferay DevCon 2016.
It attempts to make it easy for any developer to get started with Machine Learning. It presents three exercises which I'm giving as homework (yup, homework, you missed it, right? ;) to the audience.
The video for this session is now available at https://www.facebook.com/liferay/videos/vl.383534535315216/10154154247423108/?type=1 (starts at min 34)
Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it.
We will review some modern machine learning applications, understand variety of machine learning problem definitions, go through particular approaches of solving machine learning tasks.
This year 2015 Amazon and Microsoft introduced services to perform machine learning tasks in cloud. Microsoft Azure Machine Learning offers a streamlined experience for all data scientist skill levels, from setting up with only a web browser, to using drag and drop gestures and simple data flow graphs to set up experiments.
We will briefly review Azure ML Studio features and run machine learning experiment.
Activation functions and Training Algorithms for Deep Neural networkGayatri Khanvilkar
Training of Deep neural network is difficult task. Deep neural network train with the help of training algorithms and activation function This is an overview of Activation Function and Training Algorithms used for Deep Neural Network. It underlines a brief comparative study of activation function and training algorithms.
This is a single day course, allows the learner to get experience with the basic details of deep learning, first half is building a network using python/numpy only and the second half we build the more advanced netwrok using TensorFlow/Keras.
At the end you will find a list of usefull pointers to continue.
course git: https://gitlab.com/eshlomo/EazyDnn
Separating Hype from Reality in Deep Learning with Sameer FarooquiDatabricks
Deep Learning is all the rage these days, but where does the reality of what Deep Learning can do end and the media hype begin? In this talk, I will dispel common myths about Deep Learning that are not necessarily true and help you decide whether you should practically use Deep Learning in your software stack.
I’ll begin with a technical overview of common neural network architectures like CNNs, RNNs, GANs and their common use cases like computer vision, language understanding or unsupervised machine learning. Then I’ll separate the hype from reality around questions like:
• When should you prefer traditional ML systems like scikit learn or Spark.ML instead of Deep Learning?
• Do you no longer need to do careful feature extraction and standardization if using Deep Learning?
• Do you really need terabytes of data when training neural networks or can you ‘steal’ pre-trained lower layers from public models by using transfer learning?
• How do you decide which activation function (like ReLU, leaky ReLU, ELU, etc) or optimizer (like Momentum, AdaGrad, RMSProp, Adam, etc) to use in your neural network?
• Should you randomly initialize the weights in your network or use more advanced strategies like Xavier or He initialization?
• How easy is it to overfit/overtrain a neural network and what are the common techniques to ovoid overfitting (like l1/l2 regularization, dropout and early stopping)?
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8Hakky St
This is the documentation of the study-meeting in lab.
Tha book title is "Hands-On Machine Learning with Scikit-Learn and TensorFlow" and this is the chapter 8.
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...Balázs Hidasi
Slides for my RecSys 2016 talk on integrating image and textual information into session based recommendations using novel parallel RNN architectures.
Link to the paper: http://www.hidasi.eu/en/publications.html#p_rnn_recsys16
This presentation is a part of ML Course and this deals with some of the basic concepts such as different types of learning, definitions of classification and regression, decision surfaces etc. This slide set also outlines the Perceptron Learning algorithm as a starter to other complex models to follow in the rest of the course.
Artificial Intelligence, Machine Learning and Deep LearningSujit Pal
Slides for talk Abhishek Sharma and I gave at the Gennovation tech talks (https://gennovationtalks.com/) at Genesis. The talk was part of outreach for the Deep Learning Enthusiasts meetup group at San Francisco. My part of the talk is covered from slides 19-34.
Generative Adversarial Networks : Basic architecture and variantsananth
In this presentation we review the fundamentals behind GANs and look at different variants. We quickly review the theory such as the cost functions, training procedure, challenges and go on to look at variants such as CycleGAN, SAGAN etc.
발표자: 곽동현(서울대 박사과정, 현 NAVER Clova)
강화학습(Reinforcement learning)의 개요 및 최근 Deep learning 기반의 RL 트렌드를 소개합니다.
발표영상:
http://tv.naver.com/v/2024376
https://youtu.be/dw0sHzE1oAc
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...Balázs Hidasi
Slides of my presentation at CIKM2018 about version 2 of the GRU4Rec algorithm, a recurrent neural network based algorithm for the session-based recommendation task.
We discuss sampling strategies and introduce additional sampling to the algorithm. We also redesign the loss function to cope with additional sampling. The resulting BPR-max loss function is able to efficiently handle many negative samples without encountering the vanishing gradient problem. We also introduce constrained embeddings which speeds up the conversion of item representations and reduces memory usage by a factor of 4. These improvements increase offline measures up to 52%.
In the talk we also discuss online A/B test and the implications of long time observations. Most of these observations are exclusive to this talk and are not in the paper.
You can access the preprint version of the paper on arXiv: https://arxiv.org/abs/1706.03847
The code is available on GitHub: https://github.com/hidasib/GRU4Rec
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14Daniel Lewis
Piotr Mirowski (of Microsoft Bing London) presented Review of Auto-Encoders to the Computational Intelligence Unconference 2014, with our Deep Learning stream. These are his slides. Original link here: https://piotrmirowski.files.wordpress.com/2014/08/piotrmirowski_ciunconf_2014_reviewautoencoders.pptx
He also has Matlab-based tutorial on auto-encoders available here:
https://github.com/piotrmirowski/Tutorial_AutoEncoders/
Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTECBAINIDA
Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC
คณะสถิติประยุกต์ สถาบันบัณฑิตพัฒนบริหารศาสตร์ ร่วมกับ Data Science Thailand ร่วมกันจัดงาน The First NIDA Business Analytics and Data Sciences Contest/Conference
Machine learning the next revolution or just another hypeJorge Ferrer
These are the slides of my session and ModConf / Liferay DevCon 2016.
It attempts to make it easy for any developer to get started with Machine Learning. It presents three exercises which I'm giving as homework (yup, homework, you missed it, right? ;) to the audience.
The video for this session is now available at https://www.facebook.com/liferay/videos/vl.383534535315216/10154154247423108/?type=1 (starts at min 34)
Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it.
We will review some modern machine learning applications, understand variety of machine learning problem definitions, go through particular approaches of solving machine learning tasks.
This year 2015 Amazon and Microsoft introduced services to perform machine learning tasks in cloud. Microsoft Azure Machine Learning offers a streamlined experience for all data scientist skill levels, from setting up with only a web browser, to using drag and drop gestures and simple data flow graphs to set up experiments.
We will briefly review Azure ML Studio features and run machine learning experiment.
Activation functions and Training Algorithms for Deep Neural networkGayatri Khanvilkar
Training of Deep neural network is difficult task. Deep neural network train with the help of training algorithms and activation function This is an overview of Activation Function and Training Algorithms used for Deep Neural Network. It underlines a brief comparative study of activation function and training algorithms.
This is a single day course, allows the learner to get experience with the basic details of deep learning, first half is building a network using python/numpy only and the second half we build the more advanced netwrok using TensorFlow/Keras.
At the end you will find a list of usefull pointers to continue.
course git: https://gitlab.com/eshlomo/EazyDnn
Separating Hype from Reality in Deep Learning with Sameer FarooquiDatabricks
Deep Learning is all the rage these days, but where does the reality of what Deep Learning can do end and the media hype begin? In this talk, I will dispel common myths about Deep Learning that are not necessarily true and help you decide whether you should practically use Deep Learning in your software stack.
I’ll begin with a technical overview of common neural network architectures like CNNs, RNNs, GANs and their common use cases like computer vision, language understanding or unsupervised machine learning. Then I’ll separate the hype from reality around questions like:
• When should you prefer traditional ML systems like scikit learn or Spark.ML instead of Deep Learning?
• Do you no longer need to do careful feature extraction and standardization if using Deep Learning?
• Do you really need terabytes of data when training neural networks or can you ‘steal’ pre-trained lower layers from public models by using transfer learning?
• How do you decide which activation function (like ReLU, leaky ReLU, ELU, etc) or optimizer (like Momentum, AdaGrad, RMSProp, Adam, etc) to use in your neural network?
• Should you randomly initialize the weights in your network or use more advanced strategies like Xavier or He initialization?
• How easy is it to overfit/overtrain a neural network and what are the common techniques to ovoid overfitting (like l1/l2 regularization, dropout and early stopping)?
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...Simplilearn
This Deep Learning interview questions and answers presentation will help you prepare for Deep Learning interviews. This presentation is ideal for both beginners as well as professionals who are appearing for Deep Learning, Machine Learning or Data Science interviews. Learn what are the most important Deep Learning interview questions and answers and know what will set you apart in the interview process.
Some of the important Deep Learning interview questions are listed below:
1. What is Deep Learning?
2. What is a Neural Network?
3. What is a Multilayer Perceptron (MLP)?
4. What is Data Normalization and why do we need it?
5. What is a Boltzmann Machine?
6. What is the role of Activation Functions in neural network?
7. What is a cost function?
8. What is Gradient Descent?
9. What do you understand by Backpropagation?
10. What is the difference between Feedforward Neural Network and Recurrent Neural Network?
11. What are some applications of Recurrent Neural Network?
12. What are Softmax and ReLU functions?
13. What are hyperparameters?
14. What will happen if learning rate is set too low or too high?
15. What is Dropout and Batch Normalization?
16. What is the difference between Batch Gradient Descent and Stochastic Gradient Descent?
17. Explain Overfitting and Underfitting and how to combat them.
18. How are weights initialized in a network?
19. What are the different layers in CNN?
20. What is Pooling in CNN and how does it work?
Simplilearn’s Deep Learning course will transform you into an expert in deep learning techniques using TensorFlow, the open-source software library designed to conduct machine learning & deep neural network research. With our deep learning course, you’ll master deep learning and TensorFlow concepts, learn to implement algorithms, build artificial neural networks and traverse layers of data abstraction to understand the power of data and prepare you for your new role as deep learning scientist.
Why Deep Learning?
It is one of the most popular software platforms used for deep learning and contains powerful tools to help you build and implement artificial neural networks.
Advancements in deep learning are being seen in smartphone applications, creating efficiencies in the power grid, driving advancements in healthcare, improving agricultural yields, and helping us find solutions to climate change.
There is booming demand for skilled deep learning engineers across a wide range of industries, making this deep learning course with TensorFlow training well-suited for professionals at the intermediate to advanced level of experience. We recommend this deep learning online course particularly for the following professionals:
1. Software engineers
2. Data scientists
3. Data analysts
4. Statisticians with an interest in deep learning
Learn more at: https//www.simplilearn.com
Machine learning from a software engineer's perspective - Marijn van Zelst - ...Codemotion
Lot's of software engineers seem to avoid the field of machine learning because it seems hard. In this talk I want to give developers an intuition of what machine learning is using visual examples and without using mathematical formulas. I want to show that machine learning will make things possible that cannot be achieved using traditional procedural programming. I will identify high level components of a supervised machine learning algorithm: vectors, feature spaces, neural networks and labels.
Auto-Scaling Apache Spark cluster using Deep Reinforcement Learning.pdfKundjanasith Thonglek
Real-time processing is a fast and prompt processing technology that needs to complete the execution within a limited time constraint almost equal to the input time. Executing such real-time processing needs an efficient auto-scaling system which provides sufficient resources to compute the process within the time constraint. We use Apache Spark framework to build a cluster which supports real-time processing. The major challenge of scaling Apache Spark cluster automatically for the real-time processing is how to handle the unpredictable input data size and also the unpredictable resource availability of the underlying cloud infrastructure. If the scaling-out of the cluster is too slow then the application can not be executed within the time constraint as a result of insufficient resources. If the scaling-in of the cluster is slow, the resources are wasted without being utilized, and it leads less resource utilization. This research follows the real-world scenario where the computing resources are bounded by a certain number of computing nodes due to limited budget as well as the computing time is limited due to the nature of near real-time application. We design an auto-scaling system that applies a deep reinforcement learning technique, DQN (Deep Q-Network), to improve resource utilization efficiently. Our model-based DQN allows to automatically optimize the scaling of the cluster, because the DQN can autonomously learn the given environment features so that it can take suitable actions to get the maximum reward under the limited execution time and worker nodes.
This is a slide deck from a presentation, that my colleague Shirin Glander (https://www.slideshare.net/ShirinGlander/) and I did together. As we created our respective parts of the presentation on our own, it is quite easy to figure out who did which part of the presentation as the two slide decks look quite different ... :)
For the sake of simplicity and completeness, I just copied the two slide decks together. As I did the "surrounding" part, I added Shirin's part at the place when she took over and then added my concluding slides at the end. Well, I'm sure, you will figure it out easily ... ;)
The presentation was intended to be an introduction to deep learning (DL) for people who are new to the topic. It starts with some DL success stories as motivation. Then a quick classification and a bit of history follows before the "how" part starts.
The first part of the "how" is some theory of DL, to demystify the topic and explain and connect some of the most important terms on the one hand, but also to give an idea of the broadness of the topic on the other hand.
After that the second part dives deeper into the question how to actually implement DL networks. This part starts with coding it all on your own and then moves on to less coding step by step, depending on where you want to start.
The presentation ends with some pitfalls and challenges that you should have in mind if you want to dive deeper into DL - plus the invitation to become part of it.
As always the voice track of the presentation is missing. I hope that the slides are of some use for you, though.
Similar to Machine Learning Essentials Demystified part2 | Big Data Demystified (20)
Couchbase Data Platform | Big Data DemystifiedOmid Vahdaty
Couchbase is a popular open source NoSQL platform used by giants like Apple, LinkedIn, Walmart, Visa and many others and runs on-premise or in a public/hybrid/multi cloud.
Couchbase has a sub-millisecond K/V cache integrated with a document based DB, a unique and many more services and features.
In this session we will talk about the unique architecture of Couchbase, its unique N1QL language - a SQL-Like language that is ANSI compliant, the services and features Couchbase offers and demonstrate some of them live.
We will also discuss what makes Couchbase different than other popular NoSQL platforms like MongoDB, Cassandra, Redis, DynamoDB etc.
At the end we will talk about the next version of Couchbase (6.5) that will be released later this year and about Couchbase 7.0 that will be released next year.
The technology of fake news between a new front and a new frontier | Big Dat...Omid Vahdaty
קוראים לי ניצן אור קדראי ואני עומדת בצומת המעניינת שבין טכנולוגיה, מדיה ואקטיביזם.
בארבע וחצי השנים האחרונות אני עובדת בידיעות אחרונות, בהתחלה כמנהלת המוצר של אפליקציית ynet וכיום כמנהלת החדשנות.
הייתי שותפה בהקמת עמותת סטארט-אח, עמותה המספקת שירותי פיתוח ומוצר עבור עמותות אחרות, ולאחרונה מתעסקת בהקמת קהילה שמטרתה לחקור את ההיבטים הטכנולוגיים של תופעת הפייק ניוז ובניית כלים אפליקטיביים לצורך ניהול חכם של המלחמה בתופעה.
ההרצאה תדבר על תופעת הפייק ניוז. נתמקד בטכנולוגיה שמאפשרת את הפצת הפייק ניוז ונראה דוגמאות לשימוש בטכנולוגיה זו.
נבחן את היקף התופעה ברשתות החברתיות ונלמד איך ענקיות הטכנולוגיה מנסות להילחם בה.
Big Data in 200 km/h | AWS Big Data Demystified #1.3 Omid Vahdaty
What we're about
A while ago I entered the challenging world of Big Data. As an engineer, at first, I was not so impressed with this field. As time went by, I realised more and more, The technological challenges in this area are too great to master by one person. Just look at the picture in this articles, it only covers a small fraction of the technologies in the Big Data industry…
Consequently, I created a meetup detailing all the challenges of Big Data, especially in the world of cloud. I am using AWS infrastructure to answer the basic questions of anyone starting their way in the big data world.
how to transform data (TXT, CSV, TSV, JSON) into Parquet, ORCwhich technology should we use to model the data ? EMR? Athena? Redshift? Spectrum? Glue? Spark? SparkSQL?how to handle streaming?how to manage costs?Performance tips?Security tip?Cloud best practices tips?
Some of our online materials:
Website:
https://big-data-demystified.ninja/
Youtube channels:
https://www.youtube.com/channel/UCzeGqhZIWU-hIDczWa8GtgQ?view_as=subscriber
https://www.youtube.com/channel/UCMSdNB0fGmX5dXI7S7Y_LFA?view_as=subscriber
Meetup:
https://www.meetup.com/AWS-Big-Data-Demystified/
https://www.meetup.com/Big-Data-Demystified
Facebook Group :
https://www.facebook.com/groups/amazon.aws.big.data.demystified/
Facebook page (https://www.facebook.com/Amazon-AWS-Big-Data-Demystified-1832900280345700/)
Audience:
Data Engineers
Data Science
DevOps Engineers
Big Data Architects
Solution Architects
CTO
VP R&D
Making your analytics talk business | Big Data DemystifiedOmid Vahdaty
MAKING YOUR ANALYTICS TALK BUSINESS
Aligning your analysis to the business is fundamental for all types of analytics (digital or product analytics, business intelligence, etc) and is vertical- and tool agnostic. In this talk we will build on the discussion that was started in the previous meetup, and will discuss how analysts can learn to derive their stakeholders' expectations, how to shift from metrics to "real" KPIs, and how to approach an analysis in order to create real impact.
This session is primarily geared towards those starting out into analytics, practitioners who feel that they are still struggling to prove their value in the organization or simply folks who want to power up their reporting and recommendation skills. If you are already a master at aligning your analysis to the business, you're most welcome as well: join us to share your experiences so that we can all learn from each other and improve!
Bios:
Eliza Savov - Eliza is the team lead of the Customer Experience and Analytics team at Clicktale, the worldwide leader in behavioral analytics. She has extensive experience working with data analytics, having previously worked at Clicktale as a senior customer experience analyst, and as a product analyst at Seeking Alpha.
BI STRATEGY FROM A BIRD'S EYE VIEW (How to become a trusted advisor) | Omri H...Omid Vahdaty
In the talk we will discuss how to break down the company’s overall goals all the way to your BI team’s daily activities in 3 simple stages:
1. Understanding the path to success - Creating a revenue model
2. Gathering support and strategizing - Structuring a team
3. Executing - Tracking KPIs
Bios:
Omri Halak -Omri is the director of business operations at Logz.io, an intelligent and scalable machine data analytics platform built on ELK & Grafana that empowers engineers to monitor, troubleshoot, and secure mission-critical applications more effectively. In this position, Omri combines actionable business insights from the BI side with fast and effective delivery on the Operations side. Omri has ample experience connecting data with business, with previous positions at SimilarWeb as a business analyst, at Woobi as finance director, and as Head of State Guarantees at Israel Ministry of Finance.
AI and Big Data in Health Sector Opportunities and challenges | Big Data Demy...Omid Vahdaty
Lecturer has Deep experience defining Cloud computing, security models for IaaS, PaaS, and SaaS architectures specifically as the architecture relates to IAM. Deep Experience Defining Privacy protection Policy, a big fan of GDPR interpretation.
DeelExperience in Information security, Defining Healthcare security best practices including AI and Big Data, IT Security and ICS security and privacy controls in the industrial environments.
Deep knowledge of security frameworks such as Cloud Security Alliance (CSA), International Organization for Standardization (ISO), National Institute of Standards and Technology (NIST), IBM ITCS104 etc.
What Will You learn:
Every day, the website collects a huge amount of data. The data allows to analyze the behavior of Internet users, their interests, their purchasing behavior and the conversion rates. In order to increase business, big data offers the tools to analyze and process data in order to reveal competitive advantages from the data.
What Healthcare has to do with Big Data
How AI can assist in patient care?
Why some are afraid? Are there any dangers?
Aerospike meetup july 2019 | Big Data DemystifiedOmid Vahdaty
Building a low latency (sub millisecond), high throughput database that can handle big data AND linearly scale is not easy - but we did it anyway...
In this session we will get to know Aerospike, an enterprise distributed primary key database solution.
- We will do an introduction to Aerospike - basic terms, how it works and why is it widely used in mission critical systems deployments.
- We will understand the 'magic' behind Aerospike ability to handle small, medium and even Petabyte scale data, and still guarantee predictable performance of sub-millisecond latency
- We will learn how Aerospike devops is different than other solutions in the market, and see how easy it is to run it on cloud environments as well as on premise.
We will also run a demo - showing a live example of the performance and self-healing technologies the database have to offer.
ALIGNING YOUR BI OPERATIONS WITH YOUR CUSTOMERS' UNSPOKEN NEEDS, by Eyal Stei...Omid Vahdaty
ALIGNING YOUR BI OPERATIONS WITH YOUR CUSTOMERS' UNSPOKEN NEEDS
-Learn how to connect BI and product management to solve business problems
-Discover how to lead clients to ask the right questions to get the data and insight they really want
-Get pointers on saving your time and your company's resources by understanding what your customers need, not what they ask for
AWS Big Data Demystified #1.2 | Big Data architecture lessons learned Omid Vahdaty
A while ago I entered the challenging world of Big Data. As an engineer, at first, I was not so impressed with this field. As time went by, I realised more and more, The technological challenges in this area are too great to master by one person. Just look at the picture in this articles, it only covers a small fraction of the technologies in the Big Data industry…
Consequently, I created a meetup detailing all the challenges of Big Data, especially in the world of cloud. I am using AWS & GCP and Data Center infrastructure to answer the basic questions of anyone starting their way in the big data world.
how to transform data (TXT, CSV, TSV, JSON) into Parquet, ORC,AVRO which technology should we use to model the data ? EMR? Athena? Redshift? Spectrum? Glue? Spark? SparkSQL? GCS? Big Query? Data flow? Data Lab? tensor flow? how to handle streaming? how to manage costs? Performance tips? Security tip? Cloud best practices tips?
In this meetup we shall present lecturers working on several cloud vendors, various big data platforms such hadoop, Data warehourses , startups working on big data products. basically - if it is related to big data - this is THE meetup.
Some of our online materials (mixed content from several cloud vendor):
Website:
https://big-data-demystified.ninja (under construction)
Meetups:
https://www.meetup.com/Big-Data-Demystified
https://www.meetup.com/AWS-Big-Data-Demystified/
You tube channels:
https://www.youtube.com/channel/UCMSdNB0fGmX5dXI7S7Y_LFA?view_as=subscriber
https://www.youtube.com/channel/UCzeGqhZIWU-hIDczWa8GtgQ?view_as=subscriber
Audience:
Data Engineers
Data Science
DevOps Engineers
Big Data Architects
Solution Architects
CTO
VP R&D
AWS Big Data Demystified #3 | Zeppelin + spark sql, jdbc + thrift, ganglia, r...Omid Vahdaty
AWS Big Data Demystified is all about knowledge sharing b/c knowledge should be given for free. in this lecture we will dicusss the advantages of working with Zeppelin + spark sql, jdbc + thrift, ganglia, r+ spark r + livy, and a litte bit about ganglia on EMR.\
subscribe to you youtube channel to see the video of this lecture:
https://www.youtube.com/channel/UCzeGqhZIWU-hIDczWa8GtgQ?view_as=subscriber
Amazon aws big data demystified | Introduction to streaming and messaging flu...Omid Vahdaty
amazon aws big data demystified meetup:
https://www.meetup.com/AWS-Big-Data-Demystified/
Introduction to streaming and messaging flume kafka sqs kinesis
AWS Big Data Demystified #1: Big data architecture lessons learned Omid Vahdaty
AWS Big Data Demystified #1: Big data architecture lessons learned . a quick overview of a big data techonoligies, which were selected and disregard in our company
The video: https://youtu.be/l5KmaZNQxaU
dont forget to subcribe to the youtube channel
The website: https://amazon-aws-big-data-demystified.ninja/
The meetup : https://www.meetup.com/AWS-Big-Data-Demystified/
The facebook group : https://www.facebook.com/Amazon-AWS-Big-Data-Demystified-1832900280345700/
a comprehensive good introduction to the the Big data world in AWS cloud, hadoop, Streaming, batch, Kinesis, DynamoDB, Hbase, EMR, Athena, Hive, Spark, Piq, Impala, Oozie, Data pipeline, Security , Cost, Best practices
About
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Technical Specifications
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
Key Features
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface
• Compatible with MAFI CCR system
• Copatiable with IDM8000 CCR
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
Application
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Vaccine management system project report documentation..pdfKamal Acharya
The Division of Vaccine and Immunization is facing increasing difficulty monitoring vaccines and other commodities distribution once they have been distributed from the national stores. With the introduction of new vaccines, more challenges have been anticipated with this additions posing serious threat to the already over strained vaccine supply chain system in Kenya.
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...Amil Baba Dawood bangali
Contact with Dawood Bhai Just call on +92322-6382012 and we'll help you. We'll solve all your problems within 12 to 24 hours and with 101% guarantee and with astrology systematic. If you want to take any personal or professional advice then also you can call us on +92322-6382012 , ONLINE LOVE PROBLEM & Other all types of Daily Life Problem's.Then CALL or WHATSAPP us on +92322-6382012 and Get all these problems solutions here by Amil Baba DAWOOD BANGALI
#vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore#blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #blackmagicforlove #blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #Amilbabainuk #amilbabainspain #amilbabaindubai #Amilbabainnorway #amilbabainkrachi #amilbabainlahore #amilbabaingujranwalan #amilbabainislamabad
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdffxintegritypublishin
Advancements in technology unveil a myriad of electrical and electronic breakthroughs geared towards efficiently harnessing limited resources to meet human energy demands. The optimization of hybrid solar PV panels and pumped hydro energy supply systems plays a pivotal role in utilizing natural resources effectively. This initiative not only benefits humanity but also fosters environmental sustainability. The study investigated the design optimization of these hybrid systems, focusing on understanding solar radiation patterns, identifying geographical influences on solar radiation, formulating a mathematical model for system optimization, and determining the optimal configuration of PV panels and pumped hydro storage. Through a comparative analysis approach and eight weeks of data collection, the study addressed key research questions related to solar radiation patterns and optimal system design. The findings highlighted regions with heightened solar radiation levels, showcasing substantial potential for power generation and emphasizing the system's efficiency. Optimizing system design significantly boosted power generation, promoted renewable energy utilization, and enhanced energy storage capacity. The study underscored the benefits of optimizing hybrid solar PV panels and pumped hydro energy supply systems for sustainable energy usage. Optimizing the design of solar PV panels and pumped hydro energy supply systems as examined across diverse climatic conditions in a developing country, not only enhances power generation but also improves the integration of renewable energy sources and boosts energy storage capacities, particularly beneficial for less economically prosperous regions. Additionally, the study provides valuable insights for advancing energy research in economically viable areas. Recommendations included conducting site-specific assessments, utilizing advanced modeling tools, implementing regular maintenance protocols, and enhancing communication among system components.
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)MdTanvirMahtab2
This presentation is about the working procedure of Shahjalal Fertilizer Company Limited (SFCL). A Govt. owned Company of Bangladesh Chemical Industries Corporation under Ministry of Industries.
Water scarcity is the lack of fresh water resources to meet the standard water demand. There are two type of water scarcity. One is physical. The other is economic water scarcity.
Final project report on grocery store management system..pdfKamal Acharya
In today’s fast-changing business environment, it’s extremely important to be able to respond to client needs in the most effective and timely manner. If your customers wish to see your business online and have instant access to your products or services.
Online Grocery Store is an e-commerce website, which retails various grocery products. This project allows viewing various products available enables registered users to purchase desired products instantly using Paytm, UPI payment processor (Instant Pay) and also can place order by using Cash on Delivery (Pay Later) option. This project provides an easy access to Administrators and Managers to view orders placed using Pay Later and Instant Pay options.
In order to develop an e-commerce website, a number of Technologies must be studied and understood. These include multi-tiered architecture, server and client-side scripting techniques, implementation technologies, programming language (such as PHP, HTML, CSS, JavaScript) and MySQL relational databases. This is a project with the objective to develop a basic website where a consumer is provided with a shopping cart website and also to know about the technologies used to develop such a website.
This document will discuss each of the underlying technologies to create and implement an e- commerce website.
Event Management System Vb Net Project Report.pdfKamal Acharya
In present era, the scopes of information technology growing with a very fast .We do not see any are untouched from this industry. The scope of information technology has become wider includes: Business and industry. Household Business, Communication, Education, Entertainment, Science, Medicine, Engineering, Distance Learning, Weather Forecasting. Carrier Searching and so on.
My project named “Event Management System” is software that store and maintained all events coordinated in college. It also helpful to print related reports. My project will help to record the events coordinated by faculties with their Name, Event subject, date & details in an efficient & effective ways.
In my system we have to make a system by which a user can record all events coordinated by a particular faculty. In our proposed system some more featured are added which differs it from the existing system such as security.
Courier management system project report.pdfKamal Acharya
It is now-a-days very important for the people to send or receive articles like imported furniture, electronic items, gifts, business goods and the like. People depend vastly on different transport systems which mostly use the manual way of receiving and delivering the articles. There is no way to track the articles till they are received and there is no way to let the customer know what happened in transit, once he booked some articles. In such a situation, we need a system which completely computerizes the cargo activities including time to time tracking of the articles sent. This need is fulfilled by Courier Management System software which is online software for the cargo management people that enables them to receive the goods from a source and send them to a required destination and track their status from time to time.
Quality defects in TMT Bars, Possible causes and Potential Solutions.PrashantGoswami42
Maintaining high-quality standards in the production of TMT bars is crucial for ensuring structural integrity in construction. Addressing common defects through careful monitoring, standardized processes, and advanced technology can significantly improve the quality of TMT bars. Continuous training and adherence to quality control measures will also play a pivotal role in minimizing these defects.
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
TECHNICAL TRAINING MANUAL GENERAL FAMILIARIZATION COURSEDuvanRamosGarzon1
AIRCRAFT GENERAL
The Single Aisle is the most advanced family aircraft in service today, with fly-by-wire flight controls.
The A318, A319, A320 and A321 are twin-engine subsonic medium range aircraft.
The family offers a choice of engines
3. Linear regression
Finding the relation between the age
and the salary.
Predicting the salary for any given age
3
Historical
Data points
Experience
Salary
4. Historical
Data points
Salary (dependent)
Minimize the error
The Error (or Residual) is the offset of
the dependent variable from the
independent variable.
The goal of any regression is to minimize
the error for the training data and to
FIND THE OPTIMAL LINE (or curve in
case of logistic regression).
4
Error
Experience (independent)
6. Minimize the error with Stochastic Gradient
Descent (SGD)
Error =
1
𝑁 𝑖=1
𝑁
(𝑦𝑖 − 𝑦𝑖)2
N -> number of historical data points
1. Initialize some value for the slope
and intercept.
2. Find the current value of the error
function.
6
Error
Slope
Intercept
3. Find the slope at the current point (partial derivative) and move slightly
downwards in the direction.
4. Repeat until you reach a minimum OR stop after certain number of iterations
8. Multiple Linear Regression
• Simple linear regression:
𝑌 = 𝑏0 + 𝑏1*𝑥1
• Multiple linear regression:
𝑌 = 𝑏0 + 𝑏1*𝑥1 + 𝑏2*𝑥2 + … + 𝑏 𝑛∗𝑥 𝑛
Important note:
You need to exclude variables that will “mess” the prediction and keep the ones
that actually help predicting the desired result.
8
11. “Traditional” ML vs. “Representation” ML
• “Traditional” ML based systems rely on experts to decide what features to pay
attention to.
• “Representation” ML based systems figure out by themselves what features to pay
attention to.
• The most common representation ML algorithm is called Artificial Neural Network
• ANN are commonly used for:
• Image/video/audio processing
• Speech recognition
• Natural language processing (NLP)
• Games
11
13. Artificial Neural Networks - ANN
• Inspired by the neurons in the human mind.
• Can learn and organize data and thus create an understanding of relationships.
13
14. Artificial Neuron
14
Neuron
Input Signal 1 (X1)
Input Signal 2 (X2)
Input Signal n (Xn)
Output Signal
⁞
Independent variables
Dependent variable
Can be:
• Continuous (price)
• Binary (Yes/No)
• Categorical
The neuron behaves like a function
W1
W2
Wn
15. The neural network flow
In neural networks, the activation functions are non-linear.
15
17. MNIST Example
• NIST = US National Institute of Standards and
Technologies
• MNIST – a subset of NIST’s handwritten digit
data set
• Consists of a training set of 60,000 samples and
a test set of 10,000 samples.
• 28x28 pixels grayscale images and digit labels
for each image.
• http://Yann.lecun.com/exdb/mnist
17
21. Using “softmax” activation function
• In this example we will use “softmax” activation function:
• Good for classification problems.
• Increases the differences so the output gets closer to 1 or closer to 0
21
23. Minimize the error with Gradient Descent
Optimization Function
Error =
1
𝑁 𝑖=1
𝑁
𝑒𝑖
2
N -> number of historical datapoints
1. Initialize some value for the slope
and intercept.
2. Find the current value of the error
function.
23
Error
Slope
Intercept
3. Find the slope at the current point (partial derivative) and move slightly
downwards in the direction.
4. Repeat until you reach a minimum OR stop after certain number of iterations
24. Training the neural network
• How can we know what should be the weights and biases?
• Through training the network
• The code will figure out the correct values BY ITSELF
• How does the training work?
1. Starting with zero weights and bias, we multiply the input values by the weights and add the bias
2. We get an incorrect output
But we know what the correct output should be.
1. The system measures the difference between the incorrect output and the correct output. This is
call “loss measurement function”.
• The loss measurement function calculates how big the error is.
2. Now the system will change the weights and biases to minimize the error. This is called
“optimization function” and goes back to step 3 until it cannot reduce the error anymore.
24
25. Back propagation - adjusting the weights
Get Input
Values
Multiply input values by the
weights and add biases
Run activation
function and get
predictions
Calculate the
distance from the
Correct results
Apply optimization on the
weights to reduce the error
25
26. Back propagation - adjusting the weights
Get Input
Values
Multiply input values by the
weights and add biases
Run activation
function and get
predictions
Calculate the
distance from the
Correct results
Apply optimization on the
weights to reduce the error
26
9876543210
0100000000
9876543210
0.20.40.10.30.10.80.20.60.10.2
27. Back propagation - adjusting the weights
Get Input
Values
Multiply input values by the
weights and add biases
Run activation
function and get
predictions
Calculate the
distance from the
Correct results
Apply optimization on the
weights to reduce the error
27
9876543210
0100000000
9876543210
0.20.50.10.30.10.70.20.40.10.1
28. Back propagation - adjusting the weights
Get Input
Values
Multiply input values by the
weights and add biases
Run activation
function and get
predictions
Calculate the
distance from the
Correct results
Apply optimization on the
weights to reduce the error
28
9876543210
0100000000
9876543210
0.10.60.10.20.10.60.20.30.10.1
29. Back propagation - adjusting the weights
Get Input
Values
Multiply input values by the
weights and add biases
Run activation
function and get
predictions
Calculate the
distance from the
Correct results
Apply optimization on the
weights to reduce the error
29
9876543210
0100000000
9876543210
0.10.70.10.20.10.40.10.20.10.1
30. Back propagation - adjusting the weights
Get Input
Values
Multiply input values by the
weights and add biases
Run activation
function and get
predictions
Calculate the
distance from the
Correct results
Apply optimization on the
weights to reduce the error
30
9876543210
0100000000
9876543210
0.10.90.10.100.10.10.10.10.1
Correct!
33. Tensor
• An n-dimensional array or list used to represent data
• Defined by the 3 properties:
• Rank: Scalar (number), Vector (1-dim array), Matrix (2-dim array), Cube, etc.
• Shape
• Type
33
TypeShapeRankExample
Int32[]0 (scalar)1
Int32[5]1 (vector)[1, 5, 3, 6, 2]
Int32[2, 5]2 (matrix)[[1, 5, 3, 8, 4], [3, 2, 6, 4, 7] ]
Int32[3, 2, 3]3 (cube)[ [ [1, 6, 3], [2, 4, 3] ]
[ [2, 6, 2], [3, 7, 4] ]
[ [1, 9, 2], [4, 8, 3] ] ]
34. What is TensorFlow
• The most popular Python library for building ensemble algorithms – mainly NN.
• Initially developed by Google and today it is open sourced
• Provides a library of predefined versions of many common ML algorithms, but also
enables to flexibly create your own algorithm.
• Can harness the GPUs
• Scalable – using “execution master” you can run on a laptop as well as on a large
scale cluster in remote servers.
34
35. Tensor Features and Tools
• Name property - used to identify elements in the graph
• Name Scope property – used for grouping elements (like “conv1” for 1st conv layer)
• Summary class – has methods for writing summaries to log files. Can capture how
elements change over time.
• TensorBoard – A web server that uses the log files to visualize the computation
graph and training progress. Can be used from remote desktops.
• Common add-ons (for easier developement):
• TFLearn - Simplifies the use of TensorFlow only and can converse with TF data types.
• Keras – Simplification which supports multiple frameworks (including Microsoft CNTK).
35
36. Training neural networks with TensorFlow
With TensorFlow you need define the following:
1. The input data:
• “Placeholders” – The input training data.
• “Variables” – What we ask TF to compute through training. With neural network these are
weights and biases.
2. The inference function (which is applied on the weights and biases).
3. Loss/error measurement function (example: “Cross Entropy”)
4. Optimization function to minimize loss (example: “Gradient Descent”)
36
37. TensorFlow - MNIST demo
37
ImplementationConcept
MNIST dataPrepared Data
Sum(X* weight) + bias -> ActivationInference
Cross EntropyLoss Measurement
Gradient descent optimizerOptimize to minimize loss
39. Why Convolutional Neural Networks (CNN)
• Problem – Flattening the images caused us to lose the shape information.
• When we see a digit, we recognize the lines and curves.
• We need to “zoom out” slowly from the picture.
39
42. Deep Learning
• Use of multi layered neural network is called Deep Learning
• Some applications:
• Natural language processing (NLP)
• Face recognition
• Image analysis (what’s in the picture)
• Image search
• Voice analysis
• Video analysis
42
56. Filtering: The math behind the match
1. Line up the feature and the image patch.
2. Multiply each image pixel by the corresponding feature pixel.
3. Add them up.
4. Divide by the total number of pixels in the feature.
76. Pooling: Shrinking the image stack
1. Pick a window size (usually 2 or 3).
2. Pick a stride (usually 2). A stride = step.
3. Walk your window across your filtered images.
4. From each window, take the maximum value.
94. Fully connected layer
• Vote depends on how strongly a value predicts X or O
X
O
1.00
0.55
0.55
1.00
1.00
0.55
0.55
0.55
0.55
1.00
1.00
0.55
95. Fully connected layer
• Vote depends on how strongly a value predicts X or O
X
O
0.55
1.00
1.00
0.55
0.55
0.55
0.55
0.55
1.00
0.55
0.55
1.00
96. Fully connected layer
• Future values vote on X or O
X
O
0.9
0.65
0.45
0.87
0.96
0.73
0.23
0.63
0.44
0.89
0.94
0.53
97. Fully connected layer
• Future values vote on X or O
X
O
0.9
0.65
0.45
0.87
0.96
0.73
0.23
0.63
0.44
0.89
0.94
0.53
98. Fully connected layer
• Future values vote on X or O
X
O
0.9
0.65
0.45
0.87
0.96
0.73
0.23
0.63
0.44
0.89
0.94
0.53
99. Fully connected layer
• Future values vote on X or O
X
O
0.9
0.65
0.45
0.87
0.96
0.73
0.23
0.63
0.44
0.89
0.94
0.53
100. Fully connected layer
• Future values vote on X or O
X
O
0.9
0.65
0.45
0.87
0.96
0.73
0.23
0.63
0.44
0.89
0.94
0.53
101. Fully connected layer
• Future values vote on X or O
X
O
0.9
0.65
0.45
0.87
0.96
0.73
0.23
0.63
0.44
0.89
0.94
0.53
102. Fully connected layer
• A list of feature values becomes a list of votes.
X
O
0.9
0.65
0.45
0.87
0.96
0.73
0.23
0.63
0.44
0.89
0.94
0.53
103. Putting it all together
• A set of pixels becomes a set of votes.
-1 -1 -1 -1 -1 -1 -1 -1 -1
-1 1 -1 -1 -1 -1 -1 1 -1
-1 -1 1 -1 -1 -1 1 -1 -1
-1 -1 -1 1 -1 1 -1 -1 -1
-1 -1 -1 -1 1 -1 -1 -1 -1
-1 -1 -1 1 -1 1 -1 -1 -1
-1 -1 1 -1 -1 -1 1 -1 -1
-1 1 -1 -1 -1 -1 -1 1 -1
-1 -1 -1 -1 -1 -1 -1 -1 -1
X
O
Layer 1 Layer 2 Layer 3 Layer 4 Layer 5
104. Gradient descent
• For each feature pixel and voting
weight, adjust it up and down a
bit and see how the error
changes.
weighterror
105. Gradient descent
• For each feature pixel and voting
weight, adjust it up and down a
bit and see how the error
changes.
weighterror
106. Tuning the CNN
• Architecture
• How many of each type of layer?
• In what order?
• Convolution
• Number of features
• Size of features
• Pooling
• Window size
• Window stride
• Fully Connected
• Number of neurons
107. CNN - Not just for images
Things closer together are more closely related than things far away:
• 2D Images.
• 3D Images.
• Audio
• Video
• Signal processing
• NLP – semantic parsing, sentence modelling and more.
• Drug discovery - Chemical interactions,
109. Machine Learning in the near future
There is a lot of research around ML in the academia and in commercial companies
and a lot of money is invested there….
• ML will be used adopted in much greater scales across almost every industry.
• ML will be embedded everywhere
• Specialized hardware for ML will enable deeper and faster learning
• Machine Learning as a Service (MLaaS) market will grow substantially.
• ML will save more lives.
• ML will automate more repetitive tasks.
109
110. Why should developers/data
engineers/DBAs invest time in ML?
• Data is the fuel of every ML system – comes from the data platforms DBAs
manage.
• The data preparation before the training is the most time consuming part.
• The DBAs can definitely assist here.
• ML – not just for data scientists (up to a certain level)
• Developers already use ML
• Data engineers use ML.
• ML can be used by DBAs too – why not?
• ML will become more and more easy to use:
• Azure ML
• AWS ML
110