- Select a similar modeling problem 
- Create a complex model for the first task
- Reuse model from the first task on second task
- Tune and perfect the model



1) Developing your own model


https://machinelearningmastery.com/transfer-learning-for-deep-learning/

Approaches to Transfer Learning

Another approach is to use deep learning to discover the best representation of your problem, which means finding the most important features. This approach is also known as representation learning, and can often result in a much better performance than can be obtained with hand-designed representation.
In machine learning, features are usually manually hand-crafted by researchers and domain experts. Fortunately, deep learning can extract features automatically. Of course, this doesn't mean feature engineering and domain knowledge isn’t important anymore — you still have to decide which features you put into your network. That said, neural networks have the ability to learn which features are really important and which ones aren’t. A representation learning algorithm can discover a good combination of features within a very short timeframe, even for complex tasks which would otherwise require a lot of human effort.


FEATURE EXTRACTION

Pre-training in deep learning involves optimizing a neural network on an initial task before it is fine-tuned for a specific application. The core idea is that a model trained for one purpose can be successfully adapted for another. This strategy avoids the need to build complex models from the ground up, a significant advantage when dealing with tasks that have scarce labeled data. By utilizing tasks with more abundant supervision signals, pre-training reduces dependence on task-specific labels and facilitates the creation of more versatile, general-purpose models.

Pre-training in Deep Learning

- Developing your own model
- Using a pre-trained model

University of Michigan - Ann Arbor

The longest part of the development of a deep learning model is that of the training stage. However, if the problem that is being tackled has already been studied and worked on by someone else and the model has been released to the public including the trained weights then a technique to substantially increase the training process is to utilize transfer learning.

Transfer Learning in Deep Learning

https://towardsdatascience.com/transfer-learning-using-the-fastai-library-d686b238213e

Transfer Learning Reference

- Need very large dataset
- Data must be general and not domain-specific
- Only works if initial and current problem are similar enough


Disadvantages of Transfer Learning

According to DeepMind CEO Demis Hassabis, transfer learning is also one of the most promising techniques that could lead to artificial general intelligence (AGI) someday.

ideas about transfer learning from the specialist

Transfer from Task A to Task B

- Tasks A and B have the same input x
- You have a lot more data for Task A than Task B
- Low-level features from A could be helpful for learning B

When Transfer Learning in Deep Learning Makes Sense

Two Approaches to Transfer Learning in Deep Learning

An example of this concept exists in image classification. If someone wants to classify kinds of clouds it can be very difficult to compile enough data to train a model from scratch. However, models such as ImageNet have already been trained on classifying a lot more and different kinds of images so under the assumption that the earlier layers in the model hold some fundamental information about understanding images then transfer learning can be used. Then, we need to replace the output layer of the pre-trained model with a new output layer(s) that match the number of classes of the new output variable and then train the model. 

Transfer Learning in Deep Learning Example

Transfer learning has several benefits, but the main advantages are  saving training time, better performance of neural networks (in most cases), and not needing a lot of data. 

Usually, a lot of data is needed to train a neural network from scratch but access to that data isn't always available — this is where transfer learning comes in handy. With transfer learning a solid machine learning model can be built with comparatively little training data because the model is already pre-trained. This is especially valuable in natural language processing because mostly expert knowledge is required to create large labeled datasets. Additionally, training time is reduced because it can sometimes take days or even weeks to train a deep neural network from scratch on a complex task.

Learn Before

Related

Learn After