measure an AI models performance using F1 score

How to measure an AI models performance – F1 score explained

Organizations often ask us, “How well is the AI model is doing?” Or “How do I measure its performance?”, we often respond with “Performance of the AI model is based on what the F1 score of the model is” and we will get a puzzled look on everyones face or asking “what is an F1 score?”  So here I am going to attempt to explain F1 score in an easily understandable way:

Definition of F1 score:

F1 score (also F-score or F-measure) is a measure of a test’s accuracy. It considers both the precision (p) and the recall (r) of the test to compute the score (as per wikipedia)

Accuracy is how most people tend to think about it when it comes to measuring performance (Ex: How accurate is the model predicting etc.?). But accuracy is not a true measure of AI models performance. Accuracy only measures the number of correctly predicted values among the total predicted value. Although it is a good measure of performance it is not complete and does not work when the cost of false negatives is high. Ex: Lets assume we are using an AI model to predict cancer cells, after training, the model is fed with 100 samples that have cancer and the model identifies 90 samples as having cancer. That 90% accuracy, which sounds pretty high. But the cost of not identifying 10 samples is very costly. Therefore accuracy is not always the best measure.

So to explain it further lets consider this table:

 

 

True Positive:

True Positive is an outcome where the model correctly predicts the positive class. Ex: when cancer is present and the model predicts cancer.

False Positive is an outcome where the model incorrectly predicts the positive class. Ex: when cancer is not present and the model predicts cancer.

False Negative is an outcome where the model incorrectly predicts the negative class. Ex: when cancer is present and the model predicts no cancer.

True Negative is an outcome where the model correctly predicts the negative class. Ex: when cancer is not present and the model predicts no cancer.

As explained by the definition, the F1 score is a combination of Precision and Recall.

Precision is the number of True Positives divided by the number of True Positives and False Positives. Precision can be thought of as a measure of exactness. Therefore, low precision will indicate a large number of False Positives.

Recall is the number of True Positives divided by the number of True Positives and the number of False Negatives. Recall can be thought of as a measure of completeness. Therefore, low recall indicates a large number of False Negatives.

Now, F1 score is the harmonic mean of Precision and Recall and gives a much better measure of the model.

F1 Score = 2*((precision*recall)/(precision+recall)).

A good F1 score means that you have low false positives and low false negatives. Accuracy is used when the True Positives and True negatives are more important while F1-score is used when the False Negatives and False Positives are crucial

Interested in more AI insights. Click here and read our other articles.

Named Entity Recognition

Bring clarity to unstructured data using Natural Language Processing (NLP) – Part 1

Natural language processing (NLP) is a branch of artificial intelligence that helps computers understand, interpret and manipulate human language, in particular how to program computers to process and analyze large amounts of natural language data.

In my previous articles, I have addressed some specific topics on NLP like Text Classification, Natural Language Search, etc. Here I want to give a quick introduction to a few key technical capabilities of Natural Language Processing.With recent advances in Artificial intelligence technologies, computers have become very adept at reading, understanding and interpreting human language. Let’s look a few key capabilities of NLP. These are by no means a comprehensive list of all NLP capabilities.

 

Named Entity Recognition (NER):
NER is one of the first steps towards information extraction from large unstructured data. NER seeks to locate and extract named entities that are present in a text into pre-defined categories like persons, countries, organizations etc. This helps with answering many questions such as:
– How many mentions of an organization is in this article?
– Were there any specific products mentioned in a customer review?

This technology will enable organizations to extract individual entities from documents, social media, knowledge base etc. The better defined and trained the ontologies are, the more efficient the outcome will be.

 

Topic Modeling:
Topic Modeling is a type of statistical modeling for discovering abstract topics from a large document set. It is frequently used to discover hidden semantic structures in a textual body. It is different from traditional classification in that, it is an unsupervised method of extract main topics. This technique is used in the initial exploring phase to find what the common topics are in the data. Once you discover the topics, you can use language in those topics to create categories. One of the popular methods used for Topic Modeling is Latent Dirichlet Allocation (LDA). LDA builds a topic per document model and words per topic model, modeled as Dirichlet distributions. You can read more about LDA here: http://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf

 

Text Classification:
Text classification (a.k.a text categorization or text tagging) is the task of assigning a set of predefined categories to free-text. This is a supervised training methodology as opposed to Topic Modeling above. I have written in detail about text classification here:
https://abeyon.com/textclassification/

 

Information Extraction:
Information Extraction is used to automatically find meaningful information in unstructured text. Information extraction (IE) distills structured data or knowledge from the unstructured text by identifying references to named entities as well as stated relationships between such entities. IE systems can be used to directly extricate abstract knowledge from a text corpus or to extract concrete data from a set of documents which can then be further analyzed with traditional data-mining techniques to discover more general patterns.

 

Sentiment Analysis:
Sentiment analysis is the automated process of understanding an opinion about a given subject from written or spoken language. Sentiment analysis decodes the meaning behind human language, allowing organizations to analyze and interpret comments on social media platforms, documents, news articles, websites, and other venues for public comment.

 

Within government agencies and organizations, there is a deluge of unstructured data both in analog and digital form. NLP can provide the needed tools to move the needle forward in providing better visibility and knowledge into unstructured data. NLP can be utilized in many ways. To name a few: Analyze public data like Social Media, reviews, comments, etc., Get visibility into the organizational knowledge base, provide predictive capabilities, enhance citizen services, etc. There is much to be learned from the potential of AI and, in particular, its ability to analyze masses of unstructured data. It is time now for agencies and organizations to take action to harness the power of NLP to stay ahead.

Text Classification: Binary to Multi-label Multi-class classification

Unstructured data in the form of text is everywhere: emails, web pages, social media, survey responses, domain data and more. While textual data is very enriching, it is very complex to gain insights easily and classifying text manually can be hard and time-consuming. For businesses to make intelligent data-driven decisions, understanding the insights in the text in a fast and reliable way is essential. Artificial Intelligence makes that possible with Natural Language Processing (NLP) and text classification. The capability to automatically classify text into one or more categories have seen tremendous improvements in recent years. Gone are the days of manually tagging textual data which can be laborious, time-consuming, inconsistent and expensive.

So let’s look at a few types of text classification in AI.

Binary classification: As the name suggests is the process of assigning a single boolean label to textual data. Example: Reviewing an email and classifying it as good or spam.

AI Binary Classification

Multi-class classification: Multi-class classification involves the process of reviewing textual data and assigning one (single label) or more (multi) labels to the textual data. The complexity of the problem increases as the number of classes increase. Lets take an example of assigning genres to movies. Each movie is assigned one or more genres from a list of movie genres (Drama, Action, Comedy, Horror, etc.). This is a Multi-class classification problem with a manageable set of labels.

AI Multiclass classifiction

 

Now imagine a classification problem where a specific item will need to be classified across a very large category set (10,000+ categories). The problem becomes exponentially difficult. Here is where eXtreme Multi-Label Text Classification with BERT (X-BERT) comes into play. If you want to learn more about Google’s NLP framework BERT, click here.

X-BERT aims to tag each input text with the most relevant labels from an extremely large label set.

Here are a few examples of multi-class classification: Classifying a product in retail to product categories. There are hundreds of thousands of product categories (https://www.researchandmarkets.com/categories) and classifying a single product to one of category based on the product description constitutes a multi-label (specific product category) multi-class ((broader product category) example.

Displaying sponsored content based on user search queries. There are thousands of combinations of ways, users can type in a search query and in order to classify user inputs to display a specific ad under sponsored ads is another extremely large classification example.

AI based MultiLabel classification

In the work we do for the US Navy, we tackle a similar problem of identifying a single equipment name & id from a list of equipment names across ships. The need is to find the right equipment from a list of 50,000+ items with more than 90% accuracy. We utilized X-BERT model connected to additional dense layer and softmax layer to conduct fine-tuning training to identify the equipment. This combined with the subject matter expert validation and verification helped train the machine to get better over time in identifying the equipment.

Extremely Large Multi-class classification X-BERT

As shown in the examples above, with the right methodology and data training, unstructured text can be categorized automatically using AI NLP technology. Employing AI-based auto-classification will make classification more effective and efficient.

Transfer Learning

Transfer learning is a machine learning method where a model developed for a task is reused as the starting point for a model on a second task.

In transfer learning, we leverage prior knowledge from one domain into a different domain. The way transfer learning is done is by deleting the last output layer and creating a new set neural network layers for the new problem. Then these layers are trained using the new data set.

For example, let’s say you have an AI model to recognize cats, now we can use that knowledge to recognize elephants. The model for recognizing cats is created by training the model with pictures of cats (plenty on the internet). Once the model is trained to recognize cats with high accuracy, then the last layer of the neural network will be replaced with additional layers and those layers will be trained using pictures of elephants to recognize elephants. This is done so that a lot of the low-level features like detecting edges, curves, etc. could be learned from the large dataset (in this case Cats) and the newer model will be trained to recognize specific elements (elephants specific features) with fewer data as shown in the below figure.

 

Most of the success today in achieving high accuracy in AI models has been driven by extensive supervised learning which relies on large amounts of labeled datasets. For simple use cases, large amounts of labeled public data is available through various online sources (Ex: ImageNet, WordNet, etc.) but if you are building a model for a specific domain solution, large amounts of labeled data is hard to obtain or data will need to be cleaned and labeled manually for building the model. Transfer learning enables you to develop fairly accurate models using comparatively little data. This is very useful at enterprises that might not have a lot of clean labeled data.

Therefore on some problems where you may not have very much data, transfer learning will enable you to develop skillful models that you simply could not develop in the absence of transfer learning.

Knowledge Integration

Knowledge Integration in AI

So let’s think about how humans learn, we humans are very good at continuously enriching and refining our knowledge and skills by seamlessly combining existing knowledge with new experiences. We exhibit a wide spectrum of learning abilities in various fields. We can be lawyers during the day and go play tennis or go for a run in the evening and make dinner at night. We are fairly adept at doing multiple tasks. When you think about AI systems, that is usually not the case. AI systems are very good at doing a specific task through machine learning alternatively called Narrow Intelligence.

Despite recent breakthroughs and advances, machine learning has a number of shortcomings when it comes to obtaining knowledge in various fields and in developing methods to identify how new and prior knowledge interact to gain more insights. Knowledge integration is the process of synthesizing multiple knowledge representations into a common model. It represents the process of how new information and existing information interact, what effects will the new information will have on existing knowledge and if existing information needs to be modified to accommodate new information.

Why is this concept important? It is important for building a better machine learning model for enterprise knowledge insights.  Not all knowledge will be readily available or can be fed into the machine learning model at once. Substantial knowledge bases are developed incrementally and a growing body of knowledge will need to be added separately. By identifying subtle conflicts and gaps in knowledge, KI facilitates better learning models. Large firms like Google are using a combination of Symbolic AI, Deep learning and Supervised learning to create better knowledge understanding and knowledge reasoning.

If you are an organization looking to extract valuable information and identify patterns within your data to create efficiency, these concepts are critical and I highly recommend doing further research around these to achieving success.

Ai Microservice

Deploy AI Models as Microservice

Microservice is a software development technique for developing an application as a suite of small, independently deployable services built around specific business capabilities. Microservices is the idea of breaking down big, monolithic application into a collection of smaller, independent applications.

Why should machine learning models be deployed as microservices?

This is an empirical era for machine learning as successful as deep learning has been, our level of understanding of why it works so well is still lacking. Machine learning engineers need to explore and experiment with different models before they settle on a model that works for their specific use case. Once a model is developed there are inherent advantages to deploying machine learning models in a container and serving it as microservices.

Here are a few reasons to why it makes sense to deploy AI models as microservices:

  • Microservices are smaller and are easier to understand as opposed to large monolithic application. Microservices are focused around business functions and so it makes it simpler to deploy a single specific function without worrying about all the other business functions.
  • Each service can be deployed independently of each other. This also allows for independent scaling of each service as opposed to the entire application. This is a much efficient way of using computing capabilities and will achieve a balance of computing resource allocation. Microservices deployed in a container architecture allows for further efficiency in scaling.
  • Because each service is focused on a specific business function, it makes it easier for development resource(s) to understand a small set of function rather than the entire application.
  • Making the model as a service provides the ability to expose the services to both internal and external applications without having to move the code. The ability to access data using well-defined interfaces. Containers have mechanisms built in for external and distributed data access, so you can leverage common data-oriented interfaces that support many data models.
  • Each team also has the luxury of choosing whatever languages and tools they want for their job without affecting anyone else. It eliminates vendor or technology lock-in. By deploying Machine Learning models as Microservices with API endpoints, the data scientists and AI programmers can write models in whatever framework- Tensorflow, PyTorch or Keras, without worrying about the technology stack compatibility.
  • Microservices allow for deployment of new versions in parallel and independent of other services. Developers can work in parallel and get changes to production independently and faster. Enables the continuous delivery and deployment of large, complex Machine Learning applications. With production ready frameworks like Tensorflow Serving, the management of versions of a model become very easy.
  • Deploy to any environment local, private or public cloud. If there are data privacy concerns on deploying AI models on the cloud, creating individual models as containers allow for deployment of AI models in the local environment.
  • In most AI projects, there will be several AI models that will be developed to do specific functions (ex: A model to do Named Entity Recognition, Model to do Information Extraction etc.). Microservices allows for these models to be independently developed, updated and deployed.

Now let’s talk about some technologies that help with deploying models as microservices. Here we want to focus on two prominent technologies that allow for this to happen.

Docker:
Docker helps you create and deploy microservices within containers. It’s an open source collection of tools that help you build and run any app, anywhere. Here is a great resource on Docker Basics. There are plenty of resources out on the internet for getting started with Docker as well.

Kubernetes:
When it comes to deploying microservices as containers, another aspect that should be kept in mind is the management of individual containers. If you want to run multiple containers across multiple machines – which you’ll need to do if you’re using microservices, you will need to manage these efficiently. To start the right containers at the right time, make them talk to each other, handle storage and memory considerations, and deal with failed containers or hardware. Doing all of this manually would be a nightmare and hence having a tool like Kubernetes is critical. Kubernetes is an open source container orchestration platform, allowing large numbers of containers to work together in harmony, reducing operational burden.

When used together, both Docker and Kubernetes are great tools for developing a modern AI cloud architecture.

Deep Learning

What is Deep Learning?

Deep Learning is a subset of machine learning that allows machines to do tasks that typically require human like intelligence. The inspiration for deep learning comes from neuroscience, if you look at the architecture of Deep Learning Neural Networks, they are connected in a fundamental way that mirrors the brain. Deep-learning networks are distinguished from the more commonplace neural networks by their depth; that is, the number of node layers through which data passes in a multistep process.

Earlier versions of neural networks were shallow, composed of one input and one output layer, and at most one hidden layer in between. More than three layers (including input and output) qualifies as “deep” learning. So deep as strictly defined means more than one hidden layer.

Neural Network

Deep learning Neural network

In deep-learning networks, each layer of nodes trains on a distinct set of features based on the previous layer’s output. The further you advance into the neural net, the more complex the features your nodes can recognize, since they aggregate and recombine features from the previous layer.

Let’s take a simple example of recognizing hand written numbers from 1 – 10. If 10 people wrote the numbers, the numbers will look very different from each person. For a human brain, it is fairly easy to identify these numbers. For a traditional machine it is impossible to detect and hence Neural Networks are used to mimic the way, neurons in the brain interact. These multiple hidden layers allow a computer to determine the nature of a handwritten digit by providing a way for the neural network to build a rough hierarchy of different features that make up the handwritten digit.

For instance, if the input is an array of values representing the individual pixels in the image of the handwritten figure, the next layer might combine these pixels into lines and shapes, the next layer combines those shapes into distinct features like the loops in an 8 or upper triangle in a 4, and so on. By building a picture of these features, neural networks can determine with a very high level of accuracy the number that corresponds to a handwritten digit. Additionally, the model will learn which links between neurons are critical in making successful predictions during training. Over the course of several training cycles, and with the help of occasional manual tuning, the network will continue to learn and generate better predictions until it reaches desired accuracy.

Thus, Deep learning allows machines to solve complex problems even when using a data set that is very diverse, unstructured and inter-connected. Deep learning networks excel at dealing with vast amount of disparate data. In fact, the larger the amount of data the more efficient Deep learning becomes and the more deep learning algorithms learn, the better they perform.

Few additional links on this topic:
MIT Technology Review: https://www.technologyreview.com/s/513696/deep-learning/
Cambridge Univerisity paper: https://bit.ly/2Fbbrlr