Detecting Data Anomalies using Deep Learning Techniques with TensorFlow
Год выпуска: 2021
Производитель: Pluralsight
Сайт производителя://app.pluralsight.com/library/courses/detecting-data-anomalies-deep-learning-techniques-tensorflow
Автор: Andrei Pruteanu
Продолжительность: 1h 32m
Тип раздаваемого материала: Видеоурок
Язык: Английский
Описание:
This course will teach you how to create deep-learning algorithms for detecting and mitigating anomalies in data such as time series.
In this course, Detecting Data Anomalies using Deep Learning Techniques with TensorFlow 2.4, you’ll learn to spot specific patterns in large datasets that can be labelled as anomalies. First, you’ll explore how to precisely define anomalies in data. Next, you’ll discover detection algorithms. Finally, you’ll learn how to mitigate anomalous data. When you’re finished with this course, you’ll have the skills and knowledge of creating machine learning algorithms needed for dealing with various anomalies in data.
Related Topics:
[Pluralsight] Building Machine Learning Solutions with TensorFlow | Path
[Pluralsight] Build, Train, and Deploy Your First Neural Network with TensorFlow
[Pluralsight] Deep Learning with Keras
[Pluralsight] Building Image Processing Applications Using scikit-image
[Pluralsight] Building Data Visualizations Using Matplotlib
[Pluralsight] Pandas Fundamentals ► Advanced Pandas
[Pluralsight] Working with Multidimensional Data Using NumPy
[Pluralsight] Operations on Arrays with NumPy
[Pluralsight] Interpreting Data with Python | Path
[Pluralsight] How to Think About Machine Learning Algorithms
[Pluralsight] Machine Learning Literacy — Practical Application | Path
[Pluralsight] Machine Learning Literacy | Path
[Pluralsight] Deep Learning Literacy — Practical Application | Path
[Pluralsight] Deep Learning Literacy | Path
[Pluralsight] Feature Engineering | Path
[Pluralsight] Data Analytics Literacy ► Data Science Literacy | Path
[Pluralsight] Python for Data Analysts | Path
[Pluralsight] Core Python | Path
Содержание
1. Course Overview
1. Course Overview
2. Introduction
1. Introduction
2. Summary
3. Statistical Methods
4. Prerequisites
3. Exploratory Data Analysis
1. Finding a Dataset
2. Demo - EDA Part 1
3. Demo - EDA Part 2
4. Definition and Anomaly Types
1. Taxonomy
2. Real Data
5. Detection Algorithms
1. Demo - Statistical Approaches Part 1
2. Demo - Statistical Approaches Part 2
3. Demo - Deep-Learning Approaches Part 1
4. Demo - Deep-Learning Approaches Part 2
6. Mitigation Techniques
1. Techniques and Metrics
Файлы примеров: присутствуют
Субтитры: присутствуют
Формат видео: MP4
Видео: H.264/AVC, 1280x720, 16:9, 30fps, 167 kb/s
Аудио: AAC, 48.0 kHz, 96.0 kbit/s, 2 channels
