TRANSFER learning vs fine tuning

 Transfer learning is about “transferring” the learnt representations to another problem. For example one can use features from a pre-trained convolutional neural network (convNet) to power a linear support vector machine (SVM). In such a case the pre-trained model can be held fixed while the linear SVM weights can be updated.

Fine tuning on the other hand is just about making some fine adjustments to further improve performance. For example, during transfer learning, you can unfreeze the pre-trained model and let it adapt more to the task at hand.

Thus

  • Transfer learning
    • Is about projecting all new inputs through a pre-trained model. Like if we have a pre-trained model function http://www.w3.org/1998/Math/MathML"><mi>f</mi><mo stretchy="false">(</mo><mo stretchy="false">)</mo></math>">f()f() and wish to learn a new function http://www.w3.org/1998/Math/MathML"><mi>g</mi><mo stretchy="false">(</mo><mo stretchy="false">)</mo></math>">g()g(), we can simplify http://www.w3.org/1998/Math/MathML"><mi>g</mi><mo stretchy="false">(</mo><mo stretchy="false">)</mo></math>">g()g() by http://www.w3.org/1998/Math/MathML"><mi>g</mi><mo stretchy="false">(</mo><mi>f</mi><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo stretchy="false">)</mo></math>">g(f(x))g(f(x)). This way http://www.w3.org/1998/Math/MathML"><mi>g</mi><mo stretchy="false">(</mo><mo stretchy="false">)</mo></math>">g()g() sees all the data through http://www.w3.org/1998/Math/MathML"><mi>f</mi><mo stretchy="false">(</mo><mo stretchy="false">)</mo></math>">f()f().
    • Can involve fine-tuning the pre-trained model. We can fine-tune http://www.w3.org/1998/Math/MathML"><mi>f</mi><mo stretchy="false">(</mo><mo stretchy="false">)</mo></math>">f()f() as well during the learning process.
  • In machine learning (ML) the learning process itself can qualify as just fine-tuning because the update process takes very tiny steps in the opposite direction of the gradient. But fine-tuning is normally reserved as the final stage that involves setting the learning rate very low so as to fine adjust the weights. The learning process normally starts with a very poor initial state with a fairly large learning rate and then may involve a fine tuning phase with a small learning rate. You can in fact split the learning phase into multiple fine-tuning phases each with a smaller learning rate than the last.

Thus there is a difference between the two.

Comments

Post a Comment

Popular posts from this blog

Read and Navigate XML - Beautiful Soup

 ### How to read and navigate XML There is a Python library called BeautifulSoup, which makes reading in and parsing XML data easier. Here is the link to the documentation: [Beautiful Soup Documentation](https://www.crummy.com/software/BeautifulSoup/) The find() method will find the first place where an xml element occurs. For example using find('record') will return the first record in the xml file: ```xml <record>   <field name="Country or Area" key="ABW">Aruba</field>   <field name="Item" key="SP.POP.TOTL">Population, total</field>   <field name="Year">1960</field>   <field name="Value">54211</field> </record> ``` The find_all() method returns all of the matching tags. So find_all('record') would return all of the elements with the `<record>` tag. Run the code cells below to get a basic idea of how to navigate XML with BeautifulSoup. To naviga...
Read more

difference-between-stream-processing-and-message-processing

 difference-between-stream-processing-and-message-processing Message Processing implies operations on and/or using  individual  messages. Stream Processing encompasses operations on and/or using individual messages as well as operations on collection of messages as they flow into the system. For e.g., let's say transactions are coming in for a payment instrument - stream processing can be used to continuously compute hourly average spend. In this case - a sliding window can be imposed on the stream which picks up messages within the hour and computes average on the amount. Such figures can then be used as inputs to fraud detection systems Although Rabbit supports streaming, it was actually not built for it(see Rabbit´s web site) Rabbit is a Message broker and Kafka is a event streaming platform. Kafka can handle a huge number of 'messages' towards Rabbit. Kafka is a log while Rabbit is a queue which means that if once consumed, Rabbit´s messages are not there anymore in c...
Read more

WordNet in Python

Image
  WordNet   is an English dictionary which is a part of   Natural Language Tool Kit   (NLTK) for Python. This is an extensive library built to make   Natural Language Processing   (NLP) easy. Some basic functions will be discussed in this article. To start using WordNet, you have to import it first: from  nltk.corpus  import  wordnet Synsets and Lemmas In WordNet, similar words are grouped into a set known as a  Synset  (short for  Synonym-set ). Every Synset has a name, a part-of-speech, and a number. The words in a Synset are known as  Lemmas . Getting Synsets The function  wordnet.synsets('word')   returns an array  containing all the Synsets related to the word passed to it as the argument. Example: print ( wordnet.sysnets ( 'room' )) Output: [Synset(‘room.n.01’), Synset(‘room.n.02’), Synset(‘room.n.03’), Synset(‘room.n.04’), Synset(‘board.v.02’)] The method returned five Synsets; four have the name...
Read more