AI/ML

Artificial Intelligence.
For humans.
By humans.

The bots are coming; well - they aren't just on the way; they are already among us. Leverage the power of machine-driven cognitive analysis to derive insights relevant to your industry. Be it image, video, audio, speech, text or an aggregration of data types, we have developed proven techniques that can extract actionable intelligence.
Beyond the hype - AI by Ignitarium.

AI : Expertise

neural network implementations
  • Dataset preparation, labelling and validation
  • Development of algorithms and purpose-built neural networks
  • Porting of pre-trained and custom neural networks
  • Benchmarking and performance optimisation of algorithms and neural networks
  • Experience with neural network implementations on heterogenous platforms (CPU, GPU, DSP, FPGA and custom hardware accelerators)

AI : Platforms, Libraries & Frameworks

Platforms, Libraries & Frameworks

Industry Focus

  • Extensive expertise in development of algorithms related to artifact detection in industrial objects
  • Capabilities in traditional Computer Vision as well as Machine Learning techniques
  • Expertise in layer reduction and weight optimisation in industrial-targeted neural nets
  • Expertise in conducting AI-driven Design of Experiments for solving specific industrial automation tasks
  • Validation of accuracy and trainability of customer-designed industrial AI engines

Case Studies

  • Partnerships and active collaboration with the medical ecosystem
  • Experience in interpreting and labelling various categories of medical images
  • Extensive work with SegNet, U-Net, ResNet for training and inference
  • Seamless integration of medical AI implementations into IoT platforms

Case Studies

  • Extensive work with real time object detection using YOLO, MobileNet, AlexNet, ResNet
  • Expertise in OpenCV and model generation using Caffe and TensorFlow
  • Integration of object detection algorithms with connectivity frameworks
  • Optimization of image classification algorithms for operation at the Edge

Case Studies