AI & Machine Learning
Tuesday, November 17, 2020
Microsoft's CEO Satya Nadella has said: "Human Language is the new UI layer, bots are like new application". As more and more bots are getting popular in homes and enterprises, the demand for custom bots is increasing at rapid space.
The Microsoft Bot Framework is a comprehensive offering that we can use to build and deploy high-quality bots for our users to enjoy wherever they are talking.
Microsoft Cognitive Services let you build apps with powerful algorithms to see, hear, speak, understand and interpret our needs using natural methods of communication, with just a few lines of code. Easily add intelligent features – such as emotion and sentiment detection, vision and speech recognition, language understanding, knowledge, and search – into your app, across devices and platforms such as iOS, Android, and Windows, keep improving, and are easy to set up.
In this session, we will cover how to build the intelligent help desk bots in using Microsoft Power Virtual Agents, Microsoft Bot Framework and Microsoft Cognitive Services. The help desk bot will be able to answer questions related to employee benefits, open healthcare enrollment, book meeting rooms etc.
You will learn:
What are Power Virtual Agents?
What is Microsoft Bot Framework?
What is Azure Bot Service?
How to create bots using Microsoft Bot Framework?
What are Cognitive Services?
How to leverage Bot Framework and Cognitive Services to implement enterprise-grade bots?
The session will show how to make a basic classifier for Spanish data in the Transformers library. I discuss two more advanced examples: a benchmark with mixed bilingual content (LinCE), and a tool to test bias by flipping gender in Spanish sentences.
Wednesday, November 18, 2020
As we are moving mission-critical applications to the cloud, containerization is a crucial consideration. Deciding which applications to containerize was a complex activity. It required experience and understanding of application subsystems, criticality, behavior, operational requirements, engineering practices, and hosting infrastructure. Collecting the data was challenging due to the time and effort involved. Architects and developers did not have the time to conduct lengthy assessments.
We have changed this by using AI to streamline data processing and decision making. We employed continuous learning AI models to provide containerization recommendations with high accuracy and confidence while considering application characteristics, including 12-factors. We used these properties to compute the complexity of the containerization activity. AI Explainability provided the answer to why it was feasible to containerize an app. Why was the complexity low or high? Why was my risk low?
This reasoning allowed the application owners to better understand the analysis, and then they provided feedback to improve the results. Compared to traditional methods, we make containerization decisions up by 50% faster and improved accuracy by up to 40%.
Attend this session to learn more about our journey on using AI to make containerization decisions.
With the ever increasing flow of data, comes the industry focus on how to use those data for driving business & insights; but what about the size of the data these days, we have to deal with ?
The more cleaner data you have, its good for training your ML ( Machine Learning ) models, but sadly neither the world feeds you clean data nor the huge amount of data is capable of fast processing using common libraries like Pandas etc.
How about using the potential of big data libraries with support in Python to deal with this huge amount of data for deriving business insights using ML techniques? But how can we amalgamate the two?
Here comes “ PySpark : Combining Machine Learning & Big Data“.
Usually people in the ML domain prefer using Python; so combining the potential of Big Data technologies like Spark etc to supplement ML is a matter of ease with pyspark ( A Python package to use the Spark’s capabilities ).
This talk would revolve around -
1) Why do we need to fuse Big Data with Machine Learning ?
2) How Spark’s architecture will help us boost our preparations for faster ML ?
3) How pyspark’s MLlib ( Machine Learning library ) helps you do ML so seamlessly ?
Most web applications simply provide the content for the user along with a standard list of links and articles. Wouldn't it be nice to be able to customize this list of links for each user, making it a better user experience? The Azure Custom Decision Service provides contextual decision-making, allowing for a more robust user experience. It does so by converting content into features for Machine Learning. This technology utilizes several other Microsoft Cognitive Services, such as Entity Linking, Text Analytics, Emotion, and Computer Vision for a more personalized and intelligent experience.
AI and ML are frequently utilized to optimize processing, adding efficiency and improving performance of applications. Approaching the use of AI and ML from a different perspective can dramatically change the way image processing and display delivers visual data to the eyes of users. Particularly volumetric data.
Holograms have been around for a long time, but the ability to efficiently produce, transmit and display interactive holographic images has historically placed insurmountable demands on processing engines, preventing the potential to make practical consumer-level applications a reality.
Rather than trying to produce and ship the complete volumetric data package, AI and ML can be used to train cores to understand how the human brain needs to receive images for volume perception and preselect the necessary data needed by a user’s retinas, dramatically reducing the necessary transmission bandwidth and display processing demands. Such threaded volumetric processing capabilities can be utilized by developers to add differentiating holographic capabilities and features to applications.
Putting these capabilities into a developer’s toolkit can facilitate the incorporation of volumetric imagery that can be displayed through advanced depth field solutions which entice users, promote loyalty and add exponential value, thereby creating new avenues for monetization.
The speaker will highlight design tools available in standard development platforms which facilitate the incorporation of 3-D and holographic content into applications. In addition, the speaker will demonstrate ways users can be empowered to create and manipulate volumetric content on mobile devices, further expanding the application scope.