Clustering metrics better than the elbow-method
🔗 Clustering metrics better than the elbow-method
What metric to use for visualizing and determining an optimal number of clusters much better than the usual practice — elbow method.
🔗 Clustering metrics better than the elbow-method
What metric to use for visualizing and determining an optimal number of clusters much better than the usual practice — elbow method.
Medium
Clustering metrics better than the elbow-method
What metric to use for visualizing and determining an optimal number of clusters much better than the usual practice — elbow method.
Six Important Steps to Build a Machine Learning System
🔗 Six Important Steps to Build a Machine Learning System
A field guide to thinking about ML projects
🔗 Six Important Steps to Build a Machine Learning System
A field guide to thinking about ML projects
Medium
Six Important Steps to Build a Machine Learning System
A field guide to thinking about ML projects
Which flavor of data professional are you?
🔗 Which flavor of data professional are you?
A field guide to the expanding data science universe
🔗 Which flavor of data professional are you?
A field guide to the expanding data science universe
Medium
Which flavor of data professional are you?
A field guide to the expanding data science universe
What is Deep Learning and How Does it Work?
🔗 What is Deep Learning and How Does it Work?
Sit back, relax, and get comfortable with cool concepts like artificial neural networks, gradient descent, backpropagation, and more.
🔗 What is Deep Learning and How Does it Work?
Sit back, relax, and get comfortable with cool concepts like artificial neural networks, gradient descent, backpropagation, and more.
Medium
What is Deep Learning and How Does it Work?
Sit back, relax, and get comfortable with cool concepts like artificial neural networks, gradient descent, backpropagation, and more.
🎥 OpenCV Python Tutorial For Beginners 36 - Eye Detection Haar Feature based Cascade Classifiers
👁 1 раз ⏳ 433 сек.
👁 1 раз ⏳ 433 сек.
code - https://gist.github.com/pknowledge/9f380bb4ddd04274dbaffcfe634fa220
OpenCV pre-trained classifiers for face, eyes:
https://github.com/opencv/opencv/tree/master/data/haarcascades
In this video on OpenCV Python Tutorial For Beginners, we are going to see How we can do Eye Detection using Haar Feature based Cascade Classifiers.
By the end of the tutorial, you will be able to build a lane-detection algorithm fuelled entirely by Computer Vision.
OpenCV is an image processing library created by Intel anVk
OpenCV Python Tutorial For Beginners 36 - Eye Detection Haar Feature based Cascade Classifiers
code - https://gist.github.com/pknowledge/9f380bb4ddd04274dbaffcfe634fa220
OpenCV pre-trained classifiers for face, eyes:
https://github.com/opencv/opencv/tree/master/data/haarcascades
In this video on OpenCV Python Tutorial For Beginners, we are going…
OpenCV pre-trained classifiers for face, eyes:
https://github.com/opencv/opencv/tree/master/data/haarcascades
In this video on OpenCV Python Tutorial For Beginners, we are going…
Practical Experiment Fundamentals All Data Scientists Should Know
🔗 Practical Experiment Fundamentals All Data Scientists Should Know
A How-to for Non-Parametric Power Analyses, p-values, Confidence Intervals, Checking for Bias
🔗 Practical Experiment Fundamentals All Data Scientists Should Know
A How-to for Non-Parametric Power Analyses, p-values, Confidence Intervals, Checking for Bias
Medium
Practical Experiment Fundamentals All Data Scientists Should Know
A How-to for Non-Parametric Power Analyses, p-values, Confidence Intervals, Checking for Bias
Gen Z Know Automation Will Take Their Jobs
🔗 Gen Z Know Automation Will Take Their Jobs
Gen Z have their eyes on the prize, a world working with AI.
🔗 Gen Z Know Automation Will Take Their Jobs
Gen Z have their eyes on the prize, a world working with AI.
Medium
Gen Z Know Automation Will Take Their Jobs
Gen Z have their eyes on the prize, a world working with AI.
Explanation based Handwriting Verification
Authors: Mihir Chauhan, Mohammad Abuzar Shaikh, Sargur N. Srihari
Abstract: Deep learning system have drawback that their output is not accompanied with ex-planation. In a domain such as forensic handwriting verification it is essential to provideexplanation to jurors. The goal of handwriting verification is to find a measure of confi-dence whether the given handwritten samples are written by the same or different writer.We propose a method to generate explanations for the confidence provided by convolu-tional neural network (CNN) which maps the input image to 15 annotations (features)provided by experts.
https://arxiv.org/abs/1909.02548
🔗 Explanation based Handwriting Verification
Deep learning system have drawback that their output is not accompanied with ex-planation. In a domain such as forensic handwriting verification it is essential to provideexplanation to jurors. The goal of handwriting verification is to find a measure of confi-dence whether the given handwritten samples are written by the same or different writer.We propose a method to generate explanations for the confidence provided by convolu-tional neural network (CNN) which maps the input image to 15 annotations (features)provided by experts. Our system comprises of: (1) Feature learning network (FLN),a differentiable system, (2) Inference module for providing explanations. Furthermore,inference module provides two types of explanations: (a) Based on cosine similaritybetween categorical probabilities of each feature, (b) Based on Log-Likelihood Ratio(LLR) using directed probabilistic graphical model. We perform experiments using acombination of feature learning network (FLN) and each inference module. We evaluateour syst
Authors: Mihir Chauhan, Mohammad Abuzar Shaikh, Sargur N. Srihari
Abstract: Deep learning system have drawback that their output is not accompanied with ex-planation. In a domain such as forensic handwriting verification it is essential to provideexplanation to jurors. The goal of handwriting verification is to find a measure of confi-dence whether the given handwritten samples are written by the same or different writer.We propose a method to generate explanations for the confidence provided by convolu-tional neural network (CNN) which maps the input image to 15 annotations (features)provided by experts.
https://arxiv.org/abs/1909.02548
🔗 Explanation based Handwriting Verification
Deep learning system have drawback that their output is not accompanied with ex-planation. In a domain such as forensic handwriting verification it is essential to provideexplanation to jurors. The goal of handwriting verification is to find a measure of confi-dence whether the given handwritten samples are written by the same or different writer.We propose a method to generate explanations for the confidence provided by convolu-tional neural network (CNN) which maps the input image to 15 annotations (features)provided by experts. Our system comprises of: (1) Feature learning network (FLN),a differentiable system, (2) Inference module for providing explanations. Furthermore,inference module provides two types of explanations: (a) Based on cosine similaritybetween categorical probabilities of each feature, (b) Based on Log-Likelihood Ratio(LLR) using directed probabilistic graphical model. We perform experiments using acombination of feature learning network (FLN) and each inference module. We evaluateour syst
arXiv.org
Explanation based Handwriting Verification
Deep learning system have drawback that their output is not accompanied with
ex-planation. In a domain such as forensic handwriting verification it is
essential to provideexplanation to jurors....
ex-planation. In a domain such as forensic handwriting verification it is
essential to provideexplanation to jurors....
🎥 Deep Learning Full Course - 7 Hours | Deep Learning Tutorial | Edureka
👁 3 раз ⏳ 21746 сек.
👁 3 раз ⏳ 21746 сек.
** AI & Deep Learning with TensorFlow: https://www.edureka.co/ai-deep-learning-with-tensorflow **
This Edureka Deep Learning Full Course video will help you understand and learn Deep Learning & Tensorflow in detail. This Deep Learning Tutorial is ideal for both beginners as well as professionals who want to master Deep Learning Algorithms. Below are the topics covered in this Deep Learning tutorial video:
3:11 What is Deep Learning
3:55 Why Artificial Intelligence?
5:48 What is AI?
6:53 Applications of AI
8Vk
Deep Learning Full Course - 7 Hours | Deep Learning Tutorial | Edureka
** AI & Deep Learning with TensorFlow: https://www.edureka.co/ai-deep-learning-with-tensorflow **
This Edureka Deep Learning Full Course video will help you understand and learn Deep Learning & Tensorflow in detail. This Deep Learning Tutorial is ideal for…
This Edureka Deep Learning Full Course video will help you understand and learn Deep Learning & Tensorflow in detail. This Deep Learning Tutorial is ideal for…
Vijay Kumar: Flying Robots | Artificial Intelligence (AI) Podcast
🔗 Vijay Kumar: Flying Robots | Artificial Intelligence (AI) Podcast
Vijay Kumar is one of the top roboticists in the world, professor at the University of Pennsylvania, Dean of Penn Engineering, former director of GRASP lab, or the General Robotics, Automation, Sensing and Perception Laboratory at Penn that was established back in 1979, 40 years ago. Vijay is perhaps best known for his work in multi-robot systems (or robot swarms) and micro aerial vehicles, robots that elegantly cooperate in flight under all the uncertainty and challenges that real-world conditions present.
🔗 Vijay Kumar: Flying Robots | Artificial Intelligence (AI) Podcast
Vijay Kumar is one of the top roboticists in the world, professor at the University of Pennsylvania, Dean of Penn Engineering, former director of GRASP lab, or the General Robotics, Automation, Sensing and Perception Laboratory at Penn that was established back in 1979, 40 years ago. Vijay is perhaps best known for his work in multi-robot systems (or robot swarms) and micro aerial vehicles, robots that elegantly cooperate in flight under all the uncertainty and challenges that real-world conditions present.
YouTube
Vijay Kumar: Flying Robots | Lex Fridman Podcast #37
Practical guide to Attention mechanism for NLU tasks
🔗 Practical guide to Attention mechanism for NLU tasks
Tested hands-on strategies to tackle attention for improving sequence to sequence models
🔗 Practical guide to Attention mechanism for NLU tasks
Tested hands-on strategies to tackle attention for improving sequence to sequence models
Medium
Practical guide to Attention mechanism for NLU tasks
Tested hands-on strategies to tackle attention for improving sequence to sequence models
https://towardsdatascience.com/from-econometrics-to-machine-learning-ee182f3a45d7?source=collection_home---4------5----------------------
🔗 From Econometrics to Machine Learning
Why econometrics should be part of your skills
🔗 From Econometrics to Machine Learning
Why econometrics should be part of your skills
Medium
From Econometrics to Machine Learning
Why econometrics should be part of your skills
Conditional Love: The Rise of Renormalization Techniques for Conditioning Neural Networks
🔗 Conditional Love: The Rise of Renormalization Techniques for Conditioning Neural Networks
Conditional renormalization is an oft-unsung technique powering many recent ML successes; how does it work and where did the idea come…
🔗 Conditional Love: The Rise of Renormalization Techniques for Conditioning Neural Networks
Conditional renormalization is an oft-unsung technique powering many recent ML successes; how does it work and where did the idea come…
Medium
Conditional Love: The Rise of Renormalization Techniques for Conditioning Neural Networks
Conditional renormalization is an oft-unsung technique powering many recent ML successes; how does it work and where did the idea come…
Minimizing the Societal Cost of Credit Card Fraud with Limited and Imbalanced Data.
http://arxiv.org/abs/1909.01486
🔗 Minimizing the Societal Cost of Credit Card Fraud with Limited and Imbalanced Data
Machine learning has automated much of financial fraud detection, notifying firms of, or even blocking, questionable transactions instantly. However, data imbalance starves traditionally trained models of the content necessary to detect fraud. This study examines three separate factors of credit card fraud detection via machine learning. First, it assesses the potential for different sampling methods, undersampling and Synthetic Minority Oversampling Technique (SMOTE), to improve algorithm performance in data-starved environments. Additionally, five industry-practical machine learning algorithms are evaluated on total fraud cost savings in addition to traditional statistical metrics. Finally, an ensemble of individual models is trained with a genetic algorithm to attempt to generate higher cost efficiency than its components. Monte Carlo performance distributions discerned random undersampling outperformed SMOTE in lowering fraud costs, and that an ensemble was unable to outperform its individual parts. Most
http://arxiv.org/abs/1909.01486
🔗 Minimizing the Societal Cost of Credit Card Fraud with Limited and Imbalanced Data
Machine learning has automated much of financial fraud detection, notifying firms of, or even blocking, questionable transactions instantly. However, data imbalance starves traditionally trained models of the content necessary to detect fraud. This study examines three separate factors of credit card fraud detection via machine learning. First, it assesses the potential for different sampling methods, undersampling and Synthetic Minority Oversampling Technique (SMOTE), to improve algorithm performance in data-starved environments. Additionally, five industry-practical machine learning algorithms are evaluated on total fraud cost savings in addition to traditional statistical metrics. Finally, an ensemble of individual models is trained with a genetic algorithm to attempt to generate higher cost efficiency than its components. Monte Carlo performance distributions discerned random undersampling outperformed SMOTE in lowering fraud costs, and that an ensemble was unable to outperform its individual parts. Most
arXiv.org
Minimizing the Societal Cost of Credit Card Fraud with Limited and...
Machine learning has automated much of financial fraud detection, notifying
firms of, or even blocking, questionable transactions instantly. However, data
imbalance starves traditionally trained...
firms of, or even blocking, questionable transactions instantly. However, data
imbalance starves traditionally trained...
Findings of the WMT 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Condition
https://research.fb.com/publications/findings-of-the-wmt-2019-shared-task-on-parallel-corpus-filtering-for-low-resource-conditions/
https://research.fb.com/wp-content/uploads/2019/09/Findings-of-the-WMT-2019-Shared-Task-on-Parallel-Corpus-Filtering-for-Low-Resource-Conditions.pdf?
🔗 Findings of the WMT 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Conditions
Following the WMT 2018 Shared Task on Parallel Corpus Filtering (Koehn et al., 2018), we posed the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting 2% and 10% of the highest-quality data to be used to train machine translation systems. This year, the task tackled the low resource condition of Nepali– English and Sinhala–English. Eleven participants from companies, national research labs, and universities participated in this task.
https://research.fb.com/publications/findings-of-the-wmt-2019-shared-task-on-parallel-corpus-filtering-for-low-resource-conditions/
https://research.fb.com/wp-content/uploads/2019/09/Findings-of-the-WMT-2019-Shared-Task-on-Parallel-Corpus-Filtering-for-Low-Resource-Conditions.pdf?
🔗 Findings of the WMT 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Conditions
Following the WMT 2018 Shared Task on Parallel Corpus Filtering (Koehn et al., 2018), we posed the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting 2% and 10% of the highest-quality data to be used to train machine translation systems. This year, the task tackled the low resource condition of Nepali– English and Sinhala–English. Eleven participants from companies, national research labs, and universities participated in this task.
Facebook Research
Findings of the WMT 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Conditions - Facebook Research
Following the WMT 2018 Shared Task on Parallel Corpus Filtering (Koehn et al., 2018), we posed the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting 2% and 10%…
Академия искусственного интеллекта
Наш телеграм канал - tglink.me/ai_machinelearning_big_data
Урок 1. Часть 1. Искусственный интеллект сегодня
Урок 1. Часть 2. Истоки ИИ 1950-1990
Урок 1. Часть 3. Недавние вехи ИИ
Урок 1. Часть 4. Новейшие разработки ИИ
Урок 1. Часть 5. Резюме
Урок 2. Часть 1. Введение в машинное обучение
Урок 2. Часть 2. Обучение с учителем
Урок 2. Часть 3. Модели машинного обучения
Урок 2. Часть 4. Пример задачи машинного обучения
Урок 2. Часть 5. Итоги
🎥 Урок 1. Часть 1. Искусственный интеллект сегодня (Академия искусственного интеллекта)
👁 1 раз ⏳ 158 сек.
🎥 Урок 1. Часть 2. Истоки ИИ 1950-1990 (Академия искусственного интеллекта)
👁 1 раз ⏳ 298 сек.
🎥 Урок 1. Часть 3. Недавние вехи ИИ (Академия искусственного интеллекта)
👁 1 раз ⏳ 398 сек.
🎥 Урок 1. Часть 4. Новейшие разработки ИИ (Академия искусственного интеллекта)
👁 1 раз ⏳ 234 сек.
🎥 Урок 1. Часть 5. Резюме (Академия искусственного интеллекта)
👁 1 раз ⏳ 186 сек.
🎥 Урок 2. Часть 1. Введение в машинное обучение (Академия искусственного интеллекта)
👁 1 раз ⏳ 195 сек.
🎥 Урок 2. Часть 2. Обучение с учителем (Академия искусственного интеллекта)
👁 1 раз ⏳ 372 сек.
🎥 Урок 2. Часть 3. Модели машинного обучения (Академия искусственного интеллекта)
👁 1 раз ⏳ 317 сек.
🎥 Урок 2. Часть 4. Пример задачи машинного обучения (Академия искусственного интеллекта)
👁 1 раз ⏳ 265 сек.
🎥 Урок 2. Часть 5. Итоги (Академия искусственного интеллекта)
👁 1 раз ⏳ 239 сек.
Наш телеграм канал - tglink.me/ai_machinelearning_big_data
Урок 1. Часть 1. Искусственный интеллект сегодня
Урок 1. Часть 2. Истоки ИИ 1950-1990
Урок 1. Часть 3. Недавние вехи ИИ
Урок 1. Часть 4. Новейшие разработки ИИ
Урок 1. Часть 5. Резюме
Урок 2. Часть 1. Введение в машинное обучение
Урок 2. Часть 2. Обучение с учителем
Урок 2. Часть 3. Модели машинного обучения
Урок 2. Часть 4. Пример задачи машинного обучения
Урок 2. Часть 5. Итоги
🎥 Урок 1. Часть 1. Искусственный интеллект сегодня (Академия искусственного интеллекта)
👁 1 раз ⏳ 158 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 1. Часть 2. Истоки ИИ 1950-1990 (Академия искусственного интеллекта)
👁 1 раз ⏳ 298 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 1. Часть 3. Недавние вехи ИИ (Академия искусственного интеллекта)
👁 1 раз ⏳ 398 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 1. Часть 4. Новейшие разработки ИИ (Академия искусственного интеллекта)
👁 1 раз ⏳ 234 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 1. Часть 5. Резюме (Академия искусственного интеллекта)
👁 1 раз ⏳ 186 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 2. Часть 1. Введение в машинное обучение (Академия искусственного интеллекта)
👁 1 раз ⏳ 195 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 2. Часть 2. Обучение с учителем (Академия искусственного интеллекта)
👁 1 раз ⏳ 372 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 2. Часть 3. Модели машинного обучения (Академия искусственного интеллекта)
👁 1 раз ⏳ 317 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 2. Часть 4. Пример задачи машинного обучения (Академия искусственного интеллекта)
👁 1 раз ⏳ 265 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...🎥 Урок 2. Часть 5. Итоги (Академия искусственного интеллекта)
👁 1 раз ⏳ 239 сек.
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее".
Больше уроков...Vk
Урок 1. Часть 1. Искусственный интеллект сегодня (Академия искусственного интеллекта)
Академия искусственного интеллекта для школьников 7-11 классов при поддержке Сбербанка и Благотворительного фонда "Вклад в будущее". Больше уроков...
Adversarial Examples — Rethinking the Definition
🔗 Adversarial Examples — Rethinking the Definition
Adversarial examples are a large obstacle for a variety of machine learning systems to overcome. Their existence shows the tendency of…
🔗 Adversarial Examples — Rethinking the Definition
Adversarial examples are a large obstacle for a variety of machine learning systems to overcome. Their existence shows the tendency of…
Medium
Adversarial Examples — Rethinking the Definition
Adversarial examples are a large obstacle for a variety of machine learning systems to overcome. Their existence shows the tendency of…
🎥 Машинное обучение. Семинар 1. Fun with Embeddings
👁 3 раз ⏳ 1543 сек.
👁 3 раз ⏳ 1543 сек.
Семинар от 06.09.2019
Семинарист: Николай Карпачев
Ссылка на репозиторий: https://github.com/ml-mipt/ml-mipt/tree/part2_week01/part2/week01_word_embeddings
Снимал: Михаил Кревский
Монтировал: Артём СапожниковVk
Машинное обучение. Семинар 1. Fun with Embeddings
Семинар от 06.09.2019
Семинарист: Николай Карпачев
Ссылка на репозиторий: https://github.com/ml-mipt/ml-mipt/tree/part2_week01/part2/week01_word_embeddings
Снимал: Михаил Кревский
Монтировал: Артём Сапожников
Семинарист: Николай Карпачев
Ссылка на репозиторий: https://github.com/ml-mipt/ml-mipt/tree/part2_week01/part2/week01_word_embeddings
Снимал: Михаил Кревский
Монтировал: Артём Сапожников
A Keras Meta Model Served
🔗 A Keras Meta Model Served
Wrapping Keras Models into the Tensorflow Ecosystem
🔗 A Keras Meta Model Served
Wrapping Keras Models into the Tensorflow Ecosystem
Medium
A Keras Meta Model Served
Wrapping Keras Models into the Tensorflow Ecosystem