Transforming Neural Network Visualization and Interaction

About the Client

A promising company with the main focus on developing advanced AI solutions, including 3rd Generation Time-Domain Spiking Neural Networks, aiming to create flexible, powerful, and broadly applicable AI systems.
Artificial Intelligence

Company’s Request

Our client approached us to enhance their NeuroCAD tool, a software for designing Spiking Neural Networks (SNNs). They needed improvements in the user interface and additional features for better visualization, control, and management of neural networks. Their requirements included a more professional layout, the ability to delete layers, integrate different visualization options, improve error handling, and enhance the training and selection process for neural networks.

Technology Set

Used for front-end development to make the application visually appealing and functional across different devices and screen sizes.
Chosen for building dynamic and interactive user interfaces efficiently, making the UI faster and easier to maintain.
Utilized in server-side activities to handle client requests and logic, to make sure the program can handle high traffic levels and respond quickly.
Chosen for data storage and retrieval, handling diverse data types related to neural networks efficiently.
Used for data visualization, providing a framework to render complex neural network structures and connections.
Integrated for GPU acceleration, enabling faster rendering and computation of large neural network models.
Employed as a fallback for rendering large networks if Qt data visualization was slow.
Used for the algorithmic generation of 2D maps and procedural designs in the neural network connection process.
Integrated as an optional backend for breeding neural networks, allowing scalable and efficient processing.
Used for real-time communication, making updates and data synchronization happen instantly, enhancing responsiveness.
Employed for state management in React applications, providing a predictable state container that makes it easier to manage and debug application state.
Utilized for containerization, providing consistent environments for development, testing, and deployment, which simplifies dependency management.
Used for querying the API, allowing for more efficient data retrieval with the ability to request the actual data..
Integrated to add static typing to JavaScript, improving code quality and maintainability by catching errors during development and providing better tooling and documentation.

Sirin Software started by completely redesigning the layout of the NeuroCAD tool to make it more professional and user-friendly. This involved using HTML to structure the content, CSS to style, and JavaScript to make the interface interactive and compatible across different devices and screen sizes. React’s component-based design allowed us to create reusable UI elements, which improved performance and made the interface easier to maintain and update.

On the server side, we used Node.js to handle client requests and server logic efficiently. This enabled the application to manage high traffic volumes and provide quick response times, which is required for a tool that needs to process large amounts of data quickly. 

We chose MongoDB to efficiently store and manage extensive data related to neural networks and complex data structures such as neuron details, layer configurations, and connection parameters.

For visualization, we integrated Qt and CUDA to render complex neural network structures and connections. Qt provided a framework for data visualization, allowing us to create detailed visual representations of neural networks. CUDA enabled GPU acceleration, which significantly sped up the rendering process. This was important for handling large neural networks with many layers and connections, where performance can become a bottleneck. If Qt visualization was slow, we used OpenGL as a fallback for performance when Qt alone couldn’t meet the performance requirements.

We added features to delete layers, extract rendering logic, and switch between CUDA and Qt for visualization. The ability to delete layers was needed to manage and modify neural network designs easily. Extracting rendering logic from the Neuron Layer class allowed us to combine it with other visualization methods, providing more flexibility in how neural networks are displayed. Allowing users to switch between CUDA and Qt for visualization gave them the option to choose the best rendering method for their specific needs, balancing performance and visual quality.

A complete unit testing framework was put in place to guarantee that the interface visualization and error handling classes worked properly. Our team added tests for various visualization classes to verify proper rendering under varied scenarios. Error handling was also an important aspect of this framework, as it guaranteed that the program could handle and recover from unanticipated problems.

We used Python to create 2D maps that reflected the connection probabilities between neurons at different levels. These maps were used to generate procedural designs for neural network connections, guaranteeing that connections were distributed in accordance with certain patterns and regulations, which is important for building authentic and effective neural networks.

The connection page was significantly enhanced, allowing users to draw connections using Qt visualization and control the genome through the GUI. We added functionalities to draw different types of maps and widgets for each map type, making the tool more flexible and powerful. 

Users could specify connection properties with a user-friendly interface, such as the number of connections per neuron and the connection weights. This made it easier for users to design and modify neural networks according to their requirements.

For training, our team created a detailed training page that connected all fields to the Genome class, enabling testing on various types of training data. The training page was designed to be comprehensive and intuitive, allowing users to set up and monitor training sessions. We added features like a directory picker for different training data formats, a progress bar, and live training result updates to improve user experience and efficiency. The directory picker allowed users to select and organize training data in various formats, including images, videos, and text. The progress bar provided real-time feedback on the training process, while live updates allowed users to see the results as the training progressed.

The training process was enhanced to include both one-sided and two-sided training, setting up training parameters, and evaluating network performance against test criteria. One-sided training focused on training a single neural network, while two-sided training involved training two complementary networks that worked together. 

We added the ability to set various training parameters, such as the length of the training epoch and the maximum training time, to give users control over the training process. The performance of the trained networks was evaluated against predetermined criteria, to evaluate the best-performing networks for future development.

The selection and breeding pages were developed to manage the lifecycle of neural networks, from selection and deletion to breeding. We implemented logic for breeding networks on local computers or AWS, allowing for scalable and efficient processing. The selection page allowed users to select the best-performing networks based on their training results. 

The breeding page provided tools for crossbreeding selected networks to create new generations with improved performance. We added unit tests to ensure the functionality of these features, maintaining the system’s reliability and accuracy.

Value Delivered

Increased Productivity
The redesigned NeuroCAD tool streamlined our client workflow, allowing their team to work more efficiently. This meant quicker project turnarounds and the ability to take on more projects without increasing headcount, directly impacting their bottom line.
Enhanced Market Position
With the advanced features and improved usability of the NeuroCAD tool, our client positioned itself as a leader in the AI industry. This attracted new customers and strengthened relationships with existing ones, leading to increased revenue and market share.
Cost Savings
By automating manual processes and reducing errors, our client significantly lowered operational costs. This freed up resources that could be reinvested in further innovation and development, improving their competitive edge.
Risk Mitigation
Enhanced error handling and data management reduced the risk of costly mistakes and compliance issues. This not only saved money but also protected the reputation of our client.
Resource Optimization
By reducing the time and effort spent on routine tasks, our client could allocate its resources more strategically. This optimization allowed for better project management and more effective use of their team’s skills.
Increased Revenue
The combination of improved efficiency, client satisfaction, and market positioning directly contributed to increased revenue for ORBAi. The enhanced NeuroCAD tool provided a clear return on investment, driving financial growth and stability.