Deep code generation is a topic of deep learning for software engineering (DL4SE), which adopts neural models to generate code for the intended functions. Since end-to-end neural methods lack domain knowledge and software hierarchy awareness, they tend to perform poorly w.r.t project-level tasks. To systematically explore the potential improvements of code generation, we let it participate in the whole top-down development from \emph{expressibles} to \emph{executables}, which is possible in limited scopes. In the process, it benefits from massive samples, features, and knowledge. As the foundation, we suggest building a taxonomy on code data, namely code taxonomy, leveraging the categorization of code information. Moreover, we introduce a three-layer semantic pyramid (SP) to associate text data and code data. It identifies the information of different abstraction levels, and thus introduces the domain knowledge on development and reveals the hierarchy of software. Furthermore, we propose a semantic pyramid framework (SPF) as the approach, focusing on software of high modularity and low complexity. SPF divides the code generation process into stages and reserves spots for potential interactions. In addition, we conceived preliminary applications in software development to confirm the neuro-symbolic framework.

Until recently, coding involved repetitive tasks, and required knowledge of many minute details. These aspects of coding detracted from the truly creative work that developers enjoy, and they slowed developers down. Now, artificial intelligence technology promises to eliminate much of that repetitive work, and developers are no longer thrown off task by having to search the web for those minute details. The technology works similarly to auto-complete in word processing but writing code instead of plain language and completing whole functions at a time. Among the latest offerings in AI-powered is Github's Copilot, an AI-powered pair programmer tool available to all developers for $10 a month or $100 per year.

Note: This code pattern uses the classic Watson Assistant experience. After October 8, 2021, all instances (except the standard plan) can switch between the classic and new Watson Assistant experiences by going to the upper-right corner of the Watson Assistant screen and clicking the Manage icon. In this code pattern, build a framework that lets users send voice queries using the WhatsApp application and get a response from IBM Watson Assistant. The query from the user is sent to the Watson Speech to Text Service through a custom application. The output from the Watson Speech to Text Service is then fed to Watson Assistant.

In this code pattern, learn how to train a custom language and acoustic speech-to-text model to transcribe audio files to get speaker diarized output when given a corpus file and audio recordings of a meeting or classroom. One feature of the IBM Watson Speech to Text service is the capability to detect different speakers from the audio file, also known as speaker diarization. This code pattern shows this capability by training a custom language model with a corpus text file, which then trains the model with'Out of Vocabulary' words as well as a custom acoustic model with the audio files, which train the model with'Accent' detection in a Python Flask run time. Get detailed instructions in the README file. This code pattern is part of the Extracting insights from videos with IBM Watson use case series, which showcases the solution on extracting meaningful insights from videos using Watson Speech to Text, Watson Natural Language Processing, and Watson Tone Analyzer services.

In this code pattern, gain better insights and explainability by learning how to use the AI 360 Explainability Toolkits to demystify the decisions that are made by a machine learning model. This not only helps policymakers and data scientists to develop trusted explainable AI applications, but also helps with transparency for everyone. To demonstrate the use of the AI Explainability 360 Toolkit, we use the existing fraud detection code pattern explaining the AIX360 algorithms. Imagine a scenario in which you visit a bank where you want to take out a $1M loan. The loan officer uses an AI-powered system that predicts or recommends if you are eligible for a loan and how much that loan can be.

This code pattern is part of the Getting started with IBM Maximo Visual Inspection learning path. Whether you are counting cars on a road or products on a conveyor belt, there are many use cases for computer vision with video. With video as input, you can use automatic labeling to create a better classifier with less manual effort. This code pattern shows you how to create and use a classifier to identify objects in motion and then track and count the objects as they enter designated regions of interest. Whether it is car traffic, people traffic, or products on a conveyer belt, there are many applications for keeping track of potential customers, actual customers, products, or other assets. With video cameras everywhere, a business can get useful information from them with some computer vision.

How do you remove bias from the machine learning models and ensure that the predictions are fair? What are the three stages in which the bias mitigation solution can be applied? This code pattern answers these questions to help you make informed decision by consuming the results of predictive models. If you have questions about this code pattern, ask them or look for answers in the associated forum. Fairness in data and machine learning algorithms is critical to building safe and responsible AI systems.

In this developer code pattern, we will analyze insurance claims data and determine whether there are any fraudulent claims filed by users. We do this by analyzing data patterns using IBM Db2 Graph. Analysts from insurance companies can visually analyze the graph by finding patterns in data related to patients, doctor visits, multiple claims, etc. and determine whether there are suspicious claims filed. As the volume of data grows, it has become a challenge to analyze vast networks of connected data. To overcome this, there is a rapid adoption to graph database technologies, since they're built around relationships and represent data in a way that is more intuitive to read and gain insights.

This code pattern is part of the Getting started with IBM Maximo Visual Inspection learning path. In this code pattern, learn how to use optical character recognition (OCR) and the IBM Maximo Visual Inspection object recognition service to identify and read license plates. Using IBM Maximo Visual Inspection and the Custom Inference Scripts, you can build an object detection model to identify license plates from images of cars. The models in the IBM Maximo Visual Inspection object recognition service can identify portions of images that represent a license plate. Then, the post custom inference script can crop this area and use open source to perform OCR on the text to return the license plate.

Note: This code pattern uses Watson Discovery V1 and will not work with Discovery V2. However, you can still use it to learn the Discovery features. Future plans include updating the code pattern to work with Discovery V2. This code pattern explains how to create an application that you can use to search for a topic within video and audio files. While listening to a podcast or to video or audio files of courses, you often want to jump directly to the topic rather than listening to extraneous information.