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.

Abeyon Techflow Team awarded spot on HHS IAAI IDIQ Contract

Abeyon and TechFlow Team awarded a spot on $49 million HHS IAAI IDIQ contract. This contract will enable PSC contracting officers to quickly obtain Intelligent Automation/Artificial Intelligence related solutions, services, and products. The HHS Program Support Center (PSC) IAAI Contract is a multiple award, Indefinite Delivery/Indefinite Quantity (IDIQ) that supports federal agency piloting, testing and implementation of advanced technologies to include, but not limited to, intelligent automation/artificial intelligence (e.g. blockchain/distributive ledger technology (DLT), microservices, machine learning, natural language processing, robotic process automation, etc.) that are able to transform business processes and enhance mission delivery in the Federal Government.

The Program Support Center (PSC) estimates that IAAI will enable the government to run smarter, faster and more efficient. This contract is open to all federal agencies and it is the PSC’s intention to enable the public sector to shift from “low value” to “high value” tasks by automating tasks and adopting innovative solutions utilizing advanced technologies including AI and machine learning.

“Abeyon has demonstrated success in implementing robust AI solutions at DoD and we are looking to continue to bring those capabilities and add value to HHS and other federal agencies” said Mallesh Murugesan, Abeyon CEO.

Learn More