This post is the second in the series; here you will explore One-Class SVM, a semi-supervised technique for anomaly detection.

Anomaly Detection Techniques: Part 1- Understand Inter-Quartile Range, Elliptic Envelope, and Isolated Forest

Anomaly detection using Machine Learning can be divided into Supervised, Semi-Supervised, or Unsupervised algorithms.

• Supervised Anomaly Detection: A labeled dataset with inliers and outlier data points where learning happens based on the labeled dataset used for training.
• Semi-Supervised Anamoly Detection(Novelty Detection): Outliers do not pollute training data, and the anomaly detection algorithm only detects if the new observation is an inlier or an outlier. …

In this post, you will explore supervised, semi-supervised, and unsupervised techniques for Anomaly detection like Interquartile range, Isolated forest, and Elliptic envelope for identifying anomalies in data.

You might have played “Find the odd one out” as a kid where you were given a few data points like Rose, Lily, Tulip, Daffodils, and Egg Plant, and then based on the data pattern, figured out that Egg Plant was the odd one out as all the remaining items are the name of flowers and Egg Plant is a vegetable.

Anomaly detection is very similar to finding the odd one out where we analyze the data patterns in a data set to find data points that are outliers and do not comply with the normal data patterns of the…

In this article, you will learn the basics of model tracking, use Mlflow, an open-source tool for model tracking to monitor your machine learning/deep learning experiments.

What is model tracking?

Model tracking is the ability to track changes made to your models to know the differences. Some of the main changes to track in a model are

• Model Architecture,
• Model Parameters value
• Model Metrics
• Data
• Dependent libraries

How does Model tracking help?

Model Tracking helps with

• Keeping track of all the experiments that you and your team might have performed for solving a problem using ML/DL
• Comparing the different model metrics to decide which model can be promoted for production…

You will use watchdog to continuously monitor a folder to check for any new files or when an existing file is modified or deleted. When the size of the folder exceeds a certain limit, then take some action.

What is a watchdog, and how does it help?

watchdog is an open-source python API library that is a cross-platform API to monitor file system events.

You can specify a folder or a directory to watchdog observer, which keeps monitoring the folder for any changes like file creation, modification, deletion, or moving of files from one folder to another. …

Prerequisites:

A basic understanding of CNN and a sample implementation using CNN

What is GAN?

GAN is Generative Adversarial Network having two neural networks: Generator and Discriminator that are pitted against each other and are simultaneously trained by an adversarial process.

GAN has two key networks

Generator: learns to generate plausible data that is very similar to the training data. Data generated from the Generator should be indistinguishable from the real data.

Discriminator: the key objective is to distinguish between the generator’s fake data from the real data and is a simple classification network.

The Generator acts like a forger trying to trick the Discriminator by generating fake data. The Discriminator acts like a cop trying to differentiate. Between fake data and real data and in the process, both the Generator and Discriminator try to get better at their respective task. …

In this post, you will learn what ML Ops is, the difference between Dev Ops and ML Ops, the benefits of ML Ops, ML Ops components, and finally, the different maturity levels of ML Ops.

What is ML Ops?

ML Ops or Machine Learning Operations is an engineering practice and culture that combines machine learning data management, model development, experimenting with different hyperparameters, model deployment, applies automation, traceability, and monitoring at every step by building a Machine Learning pipeline.

It is a collaboration between Data Scientists, Data Engineers, and Operation Professionals to ensure a repeatable, traceable, and automated high-quality machine learning pipeline that is easy to create, maintain, deploy, and monitor. …

Here you will go step by step to perform object detection on a custom dataset using TF2 Object Detection API and some of the issues and resolutions.

The custom dataset is available here.

TensorFlow 2 Object detection model is a collection of detection models pre-trained on the COCO 2017 dataset.

Tensorflow 2 Object Detection API in this article will identify all the kangaroo’s present in an image or video, along with their locations. Locations of kangaroo will be depicted by drawing bounding boxes.

Steps for performing Object Detection on a Custom Dataset using TF2 Object Detection API

Step1 : Setup for TensorFlow2 Object Detection API

Clone the TensorFlow Models repository

git clone https://github.com/tensorflow/models.git

You should have the following directory structure.

Learn the Audio analysis basics to convert Audio files to numerical data and perform Audio classification on MNIST Audio data.

Here you will learn the basics of Audio analysis of wav files, convert Audio files to numerical data using Short Term Fourier Transformation(STFT) and. Mel Frequency Cepstral Coefficient (MFCC), extract the audio data's necessary features and finally perform the Audio classification on MNIST Audio data.

How to read a wav file or any Audio file?

Import librosa for Audio analysis. It is a Python package for audio and music signal processing.

pip install librosa

Sound is a wave-like vibration, an analog signal that has a Frequency and an Amplitude. …