How Transparent Do You Think Deep Learning Models Are?

June 9, 2023

In this article, we discuss the epistemological nature of deep learning models and how to tackle their uncertainties.



While algorithm bias in deep learning models may not sound serious at first, it is indeed a significant concern. In sectors like medicine, national safety, business automation, and climatology, recognizing that deep learning is not a one-size-fits-all solution for predicting everything. For instance, companies that rely on data-driven decisions are vulnerable to challenges caused by inaccurate predictions. The same goes for other sectors as well. Deep learning models are trained on a sample dataset  that is representative of a broader population. However, the randomness of real-world data can be a challenge to these models. . This is exactly what the epistemic uncertainty of the deep learning model means.

In simple terms, this kind of uncertainty arises from the deficiency in the variety of historical data that the model is trained on. For instance, we cannot expect a deep learning model to recognize a picture of a bird when it is trained on a neural network that identifies cats and dogs. The situation gets worse as our problem gets complex. In this article, we will discuss how the epistemic uncertainty in deep learning arises and the methods that can be used to solve it.

Breaking Down the Concept of Epistemic Uncertainty in Deep Learning Models

Understanding the epistemic uncertainty of a deep learning model is important in risk-based decision-making and safety-critical applications. It is important because we need to know how reliable the model is. It arises mainly due to two major reasons: 

  1. Inadequate amount of training data or noisy training data 

Consider the following dataset of handwritten digits, the famous MNIST dataset:

While humans are blessed with the visual cortex to differentiate between digits, it becomes a mundane task to train a neural network because it has to learn from each pixel and determine which curves and edges form a digit. Also, the above training data is not enough for the model to perceive a digit when a number is provided as input by a person who has completely different handwriting altogether. Or in statistical terms, we can say that the probability of identifying some random person’s handwriting is very less if it doesn’t pertain to the sample set provided above. 

Also, there is a lot of noise in this dataset. For example, take this image:

Is it a scar? Is it a point? Or is it even a number? According to the MNIST dataset, it's the digit “8”. Such noisy data values further contribute to the epistemic uncertainty of deep learning models. 

  1. Noise arises while training the deep learning model

While training a deep neural network there are a lot of weights and biases involved which makes the whole network noisy and produces vague outputs. 


The above neural network just has two hidden layers with probably millions of calculations. Noise is bound to occur while training more complex data. 

Methods Employed to Tackle the Uncertainty

  • Monte-Carlo Dropout
  • Deep Ensembles
  • Quantile Regression
  1. Monte-Carlo Dropout     

To understand Monte-Carlo Dropout we need to first break down the terms. Dropout in deep learning means some of the neurons in the deep neural networks are randomly dropped to avoid overfitting during the training process. Monte-Carlo Dropout takes this process further by dropping random neurons even during the testing process. Let us better understand this with the analogy of the roulette game. 

The player chooses some random set of numbers and bets on it. The bets are the training data points. After spinning the wheel, the ball is dropped onto it. This process is done multiple times, but by skipping random numbers. The same is performed during the testing process to generate the winning outcomes when the ball eventually comes to rest. In each test run, there is a slightly different outcome due to the dropout of numbers. Thus, the different numbers generated during the spin help us to understand how uncertain or confident the game can be. 

  1. Deep Ensembles

Deep ensembles make use of multiple deep neural networks to improve their performance, hence reducing the uncertainty and increasing the accuracy of the model. Let’s take the example of Beth Harmon, the fictional American chess prodigy from the popular series, The Queen’s Gambit. 

Beth learned to play chess from her janitor in the orphanage where she lived. Mr. Shaibel trained her well and they used to play regularly in the basement. This is analogous to a single deep learning model that is trained on some data. Later on in the show, Beth is introduced to various tournaments where she meets players and learns from their moves as well. The show ends with a grand ending where she beats the world champion after a very long series of tournaments. She learns from her own opponents and is beautifully able to use it against them. The other players are analogous to individual deep learning models that help enhance the performance of Beth.

  1. Quantile Regression:  

Quantile regression is a technique used to remove epistemic uncertainty during training by using the loss function. Setting house prices is one of the most common examples used to explain deep learning to beginners.

The sale price of a house is a very crucial factor in the housing industry. Thus, it is the target variable. The target variable depends upon various factors which are known as the predictor variable. The predictor variables are square foot area, number of bedrooms, location, and so on. These predictor variables are used to determine the various quantiles of the house price. 

Quantiles divide the house price into different percentiles. Quantile regression captures how changes in predictor variables affect the house price at various percentiles. For instance, the location of the house may have a significant effect on the upper percentiles as compared to the lower percentiles. Hence, such models are robust and correctly predict the prices of outliers.


In this article we saw how the epistemic uncertainty of deep learning arises and can be dealt with. The various techniques to predict the uncertainties make the models faster and more reliable in critical applications. The examples depicted in the article were real-life connections to how deep neural networks mimic them. The examples were illustrated so that the readers get a better understanding of the concepts used to tackle the uncertainty in deep learning models. 

E2E Cloud's competitive pricing and exceptional performance have positioned it as an ideal choice for data scientists, AI researchers, and technical professionals seeking an enhanced GPU Jupyter Notebook experience. By offering cost-effective GPU instances and ensuring top-notch performance, E2E Cloud enables users to leverage the power of NVIDIA GPUs without compromising on their budget.

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