A Comprehensive Hands on guide to transfer learning

August 29, 2022


Machine learning and deep learning techniques largely designed in a way that we have to train and test models every time for each new problem we want to solve, as each problem has unique set of dataset and classes distribution, while in opposed to this Transfer learning means the applications of skills and knowledge that were learned and acquired in one task to another related learning task or situation.

Concept of transfer learning can be understood by the way humans learn from other subject matter experts. Analogy would go something like this: A teacher has a huge expertise in the subject he/she teaches. It is beneficial for students to get all the information through a lecture or classes from the teacher. In this case ‘transfer’ of knowledge from teacher to student is being done. 

Other, example of transfer learning could be,

  • Knowing how to play classic piano helps in learning jazz piano
  • Knowing math and statistics helps in learning machine learning techniques

In this blog, we are going to cover detailed understanding of Transfer learning, Types of Transfer learning and real-world applications of transfer learning.

Table of Contents:

  1. Understanding Transfer learning 
  2. Transfer learning for deep learning 
  3. Types of Transfer learning
  4. Applications of transfer learning 
  5. Advantages of Transfer learning
  6. Real-world use-cases of Transfer learning

Understanding of Transfer learning:

To gain understanding of transfer learning, we first understand the difference between the traditional approach of building and training machine learning models, and the concept of transfer learning.

Traditional machine learning is isolated and knowledge gained or acquired from one task based on a set of dataset remains isolated. No knowledge or skills are transferred or retrained to related tasks of other sets of datasets.

In transfer learning, you can leverage knowledge in the form of parameters or weights from previously trained models for training newer models and even solve problems that have very little data available which is the case most of the time in industry and business environments.

To apply transfer learning methods in business or industry use-cases one should answer three questions:

  1. What to transfer: this tells which part of existing knowledge needs to be transferred to the new task
  2. When to transfer: this question answers in which task transfer learning helps in to improve accuracy of given task
  3. How to transfer: this tells which exact method to use in order to transfer knowledge on models to others.

Transfer learning for Deep Learning 

The inductive learning method is exemplified by deep learning models. To infer a mapping from a set of training instances is the goal of inductive learning methods. For instance, the model learns how to link input features to class labels in classification scenarios. Such a learner relies on a set of assumptions about the distribution of the training data in order to generalize successfully to new data. Inductive bias is the term used to describe these sets of presumptions. Numerous characteristics, such as the hypothesis space it confines to and the search procedure through the hypothesis space, can be used to describe the inductive bias. Therefore, these biases affect what and how the model learns about the given task and domain.

Transfer learning is a concept which allows to reuse trained model instead training from scratch:

  • Take a network trained on a different domain for a different source task from where model was originally trained 
  • Adapt it for your new domain or target problem at hand

Now, let’s look at some of strategies used in transfer learning for Deep learning 

  1. Feature extraction: 

Layered architectures used in deep learning systems and models allow for the learning of various features at various layers (hierarchical representations of layered features). To obtain the final output, these layers are finally connected to a final layer (often a fully connected layer in the case of supervised learning).

“The key idea here is to just leverage the pre-trained model’s weighted layers to extract features but not to update the weights of the model’s layers during training with new data for the new task.”

  1. Fine tuning:

Fine tuning consists of unfreezing a few of the top layers of a frozen model base used for feature extraction, and jointly training both the newly added part of the model and these top layers. This Is nothing but the Fine-tuning because it slightly adjusts the more abstract representations of the model being reused, in order to make them more relevant for the problem at hand.

Now, let’s look at the pre-trained models that are used in transfer learning for deep learning model development:

Everyone can use pre-trained models thanks to a variety of methods. An interface for downloading various well-liked models is provided by the renowned deep learning Python library ‘keras’. Pre-trained models are also available online because the majority of them are open-sourced.

For computer vision:

  • Xception
  • Inception V3
  • ResNet50
  • VGG16
  • VGG19
  • MobileNet
  • MobileNetV2

For Natural language processing:

  • Word2Vec
  • GloVe
  • FastText
  • BERT
  • GPT3
  • Roberta
  • XLM
  • FlauBERT

Types of Transfer Learning 

The words related with transfer learning have been used broadly and frequently interchangeably throughout the literature's many incarnations, as was indicated at the beginning of this chapter. Therefore, differentiating between transfer learning, domain adaptation, and multi-task learning can be difficult at times.

  1. Domain Adaption:

Domain adaption is usually referred to in scenarios where the marginal probabilities between the source and target domains are different, such as P(Xₛ) ≠ P(Xₜ).

  1. Domain Confusion:

We talked about the potential applications of feature-representation transfer. It is important to emphasise once more that different layers in a deep learning network capture various feature set. This fact allows us to acquire domain-invariant features and enhance their domain portability. We push both domains' representations to be as comparable as feasible rather than letting the model learn any representation. This can be done by directly applying specific pre-processing procedures to the representations. The idea behind this technique is to add another objective to the source model to encourage similarity by confusing the domain itself, hence the domain confusion.

  1. Multitask learning:

In this technique, several tasks are learned simultaneously without distinction between the source and target. As opposed to transfer learning, where the learner initially has no knowledge of the target task, in this situation the learner learns information about numerous tasks at once.

Applications of Transfer learning

  1. Transfer learning for NLP:

Textual data provides a variety of difficulties for ML and deep learning. These are typically vectorized or converted using various methods. Various training datasets have been used to create embeddings like Word2vec and FastText.

  1. Transfer learning for Audio/Speech:

Automatic Speech Recognition (ASR) models created for English have been utilized successfully to boost German speech recognition performance. Another area where transfer learning has been quite helpful is automatic speaker identification.

  1. Transfer learning for Computer Vision:

Using various CNN architectures, deep learning has been used relatively well for a variety of computer vision tasks, including object detection and identification.

Advantages of transfer learning

We saw, what are the types of transfer learning, and applications of it, now let’s look at some of the advantages of transfer learning

  1. It helps in solving complex real-world problems with several constraints. 
  2. Helps solve problems where we have little or no labelled data available 
  3. Ease of transferring knowledge in form of parameters from one model to another based on specific problem or task.

Real-world use-cases of Transfer learning

  1. Image classification or Object recognition tasks such as Dog vs Cat classification, natural images like, forest, mountain, glacier, etc. classification.
  2. Personalized Display of products in shopping Mall/offline stores, etc.
  3. Multiclass image classification with less data availability
  4. Spam detection and filtering using BERT and GPT3 pre-trained models
  5. Image captioning using VGG16 as an encoder and BERT decoder


In this article, we saw detailed understanding of Transfer learning techniques, types of transfer learning are available in deep learning. Also, we saw some of the real-world applications and use-cases of transfer learning in deep learning.


[1] Data analytics using Python by Bharti Motwani

[2] Deep learning with Python by Francois Chollet

[3] https://towardsdatascience.com/a-comprehensive-hands-on-guide-to-transfer-learning-with-real-world-applications-in-deep-learning-212bf3b2f27a

Latest Blogs
This is a decorative image for: A Complete Guide To Customer Acquisition For Startups
October 18, 2022

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

  • Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

  • MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
  • CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.  
  • CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
  • Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

  • Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

  • Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels. 

  • Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

Reference Links




This is a decorative image for: Constructing 3D objects through Deep Learning
October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

  • Highly calibrated cameras that take a photograph of the image from various angles.
  • Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

  • Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

  • Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

  • Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

  • Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

  • Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

  • 3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
  • It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
  • They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
  • It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
  • It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website

Reference Links



This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts
October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning   is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

  1. Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
  2. Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
  3. Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
  4. Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.  

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links



This is a decorative image for: GAUDI: A Neural Architect for Immersive 3D Scene Generation
October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

  • The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
  • Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
  • GAUDI also removes GANs pathologies like mode collapse and improved GAN.
  • GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

  • Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
  • This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
  • The scenes are thus synthesized by interpolation within the hidden space.
  • The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
  • A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

Reference Links




Build on the most powerful infrastructure cloud

A vector illustration of a tech city using latest cloud technologies & infrastructure