1604656402

Neural Network uses optimising strategies like stochastic gradient descent to minimize the error in the algorithm. The way we actually compute this error is by using a Loss Function. It is used to quantify how good or bad the model is performing. These are divided into two categories i.e.Regression loss and Classification Loss.

#100daysofcode #regression #algorithm #data-science #data #keras

1618317562

View more: https://www.inexture.com/services/deep-learning-development/

We at Inexture, strategically work on every project we are associated with. We propose a robust set of AI, ML, and DL consulting services. Our virtuoso team of data scientists and developers meticulously work on every project and add a personalized touch to it. Because we keep our clientele aware of everything being done associated with their project so there’s a sense of transparency being maintained. Leverage our services for your next AI project for end-to-end optimum services.

#deep learning development #deep learning framework #deep learning expert #deep learning ai #deep learning services

1603735200

The Deep Learning DevCon 2020, DLDC 2020, has exciting talks and sessions around the latest developments in the field of deep learning, that will not only be interesting for professionals of this field but also for the enthusiasts who are willing to make a career in the field of deep learning. The two-day conference scheduled for 29th and 30th October will host paper presentations, tech talks, workshops that will uncover some interesting developments as well as the latest research and advancement of this area. Further to this, with deep learning gaining massive traction, this conference will highlight some fascinating use cases across the world.

Here are ten interesting talks and sessions of DLDC 2020 that one should definitely attend:

**Also Read:** Why Deep Learning DevCon Comes At The Right Time

**By Dipanjan Sarkar**

**About: **Adversarial Robustness in Deep Learning is a session presented by Dipanjan Sarkar, a Data Science Lead at Applied Materials, as well as a Google Developer Expert in Machine Learning. In this session, he will focus on the adversarial robustness in the field of deep learning, where he talks about its importance, different types of adversarial attacks, and will showcase some ways to train the neural networks with adversarial realisation. Considering abstract deep learning has brought us tremendous achievements in the fields of computer vision and natural language processing, this talk will be really interesting for people working in this area. With this session, the attendees will have a comprehensive understanding of adversarial perturbations in the field of deep learning and ways to deal with them with common recipes.

Read an interview with Dipanjan Sarkar.

**By Divye Singh**

**About: **Imbalance Handling with Combination of Deep Variational Autoencoder and NEATER is a paper presentation by Divye Singh, who has a masters in technology degree in Mathematical Modeling and Simulation and has the interest to research in the field of artificial intelligence, learning-based systems, machine learning, etc. In this paper presentation, he will talk about the common problem of class imbalance in medical diagnosis and anomaly detection, and how the problem can be solved with a deep learning framework. The talk focuses on the paper, where he has proposed a synergistic over-sampling method generating informative synthetic minority class data by filtering the noise from the over-sampled examples. Further, he will also showcase the experimental results on several real-life imbalanced datasets to prove the effectiveness of the proposed method for binary classification problems.

**By Dongsuk Hong**

**About:** This is a paper presentation given by Dongsuk Hong, who is a PhD in Computer Science, and works in the big data centre of Korea Credit Information Services. This talk will introduce the attendees with machine learning and deep learning models for predicting self-employment default rates using credit information. He will talk about the study, where the DNN model is implemented for two purposes — a sub-model for the selection of credit information variables; and works for cascading to the final model that predicts default rates. Hong’s main research area is data analysis of credit information, where she is particularly interested in evaluating the performance of prediction models based on machine learning and deep learning. This talk will be interesting for the deep learning practitioners who are willing to make a career in this field.

#opinions #attend dldc 2020 #deep learning #deep learning sessions #deep learning talks #dldc 2020 #top deep learning sessions at dldc 2020 #top deep learning talks at dldc 2020

1593529260

In the previous blog, we looked into the fact why Few Shot Learning is essential and what are the applications of it. In this article, I will be explaining the Relation Network for Few-Shot Classification (especially for image classification) in the simplest way possible. Moreover, I will be analyzing the Relation Network in terms of:

- Effectiveness of different architectures such as Residual and Inception Networks
- Effects of transfer learning via using pre-trained classifier on ImageNet dataset

Moreover, effectiveness will be evaluated on the accuracy, time required for training, and the number of required training parameters.

Please watch the GitHub repository to check out the implementations and keep updated with further experiments.

In few shot classification, our objective is to design a method which can identify any object images by analyzing few sample images of the same class. Let’s the take one example to understand this. Suppose Bob has a client project to design a 5 class classifier, where 5 classes can be anything and these 5 classes can even change with time. As discussed in previous blog, collecting the huge amount of data is very tedious task. Hence, in such cases, Bob will rely upon few shot classification methods where his client can give few set of example images for each classes and after that his system can perform classification young these examples with or without the need of additional training.

In general, in few shot classification four terminologies (N way, K shot, support set, and query set) are used.

**N way:**It means that there will be total N classes which we will be using for training/testing, like 5 classes in above example.**K shot:**Here, K means we have only K example images available for each classes during training/testing.**Support set:**It represents a collection of all available K examples images from each classes. Therefore, in support set we have total N*K images.**Query set:**This set will have all the images for which we want to predict the respective classes.

At this point, someone new to this concept will have doubt regarding the need of support and query set. So, let’s understand it intuitively. Whenever humans sees any object for the first time, we get the rough idea about that object. Now, in future if we see the same object second time then we will compare it with the image stored in memory from the when we see it for the first time. This applied to all of our surroundings things whether we see, read, or hear. Similarly, to recognise new images from query set, we will provide our model a set of examples i.e., support set to compare.

And this is the basic concept behind Relation Network as well. In next sections, I will be giving the rough idea behind Relation Network and I will be performing different experiments on 102-flower dataset.

The Core idea behind Relation Network is to learn the generalized image representations for each classes using support set such that we can compare lower dimensional representation of query images with each of the class representations. And based on this comparison decide the class of each query images. Relation Network has two modules which allows us to perform above two tasks:

**Embedding module:**This module will extract the required underlying representations from each input images irrespective of the their classes.**Relation Module:**This module will score the relation of embedding of query image with each class embedding.

**Training/Testing procedure:**

We can define the whole procedure in just 5 steps.

- Use the support set and get underlying representations of each images using embedding module.
- Take the average of between each class images and get the single underlying representation for each class.
- Then get the embedding for each query images and concatenate them with each class’ embedding.
- Use the relation module to get the scores. And class with highest score will be the label of respective query image.
- [Only during training] Use MSE loss functions to train both (embedding + relation) modules.

Few things to know during the training is that we will use only images from the set of selective class, and during the testing, we will be using images from unseen classes. For example, from the 102-flower dataset, we will use 50% classes for training, and rest will be used for validation and testing. Moreover, in each episode, we will randomly select 5 classes to create the support and query set and follow the above 5 steps.

That is all need to know about the implementation point of view. Although the whole process is simple and easy to understand, I’ll recommend reading the published research paper, Learning to Compare: Relation Network for Few-Shot Learning, for better understanding.

#deep-learning #few-shot-learning #computer-vision #machine-learning #deep learning #deep learning

1596240720

Loss functions are used to calculate the difference between the predicted output and the actual output. To know how they fit into neural networks, read :

In this article, I’ll explain various loss functions for regression, their advantages, and disadvantages using which, you can select the right one for your project.

Loss functions are fundamentally dependent on the nature of our dependent variables and so, to select a loss function, we must examine if our dependent variables are numeric (in regression task) or probabilistic (in a classification task).

When we are dealing with numeric variables, we have to measure the losses numerically, meaning, just knowing if the predicted value is wrong is not enough, we have to calculate the amount of deviation of our prediction from the actual value, so we can train our network accordingly.

**The different loss functions for this are :**

- Mean Absolute Error (MAE).
- Mean Absolute Percentage Error (MAPE).
- Mean Squared Error (MSE).
- Root Mean Squared Error (RMSE).
- Huber Loss.
- Log-Cosh Loss.

MAE is the simplest error function, it literally just calculates the **absolute difference** (discards the sign) between the actual and predicted values and takes it’s mean.

MAE Equation from Data Vedas

The following figure shows that the MAE increases linearly with an increase in error.

Image by author

- MAE is the simplest method to calculate the loss.
- Due to its simplicity, it is computationally inexpensive.

- MAE calculates loss by considering all the errors on the same scale. For example, if one of the output is on the scale of hundred while other is on the scale of thousand, our network won’t be able to distinguish between them just based on MAE, and so, it’s hard to alter weights during backpropagation.
- MAE is a linear scoring method, i.e. all the errors are weighted equally while calculating the mean. This means that while backpropagation, we may just jump past the minima due to MAE’s steep nature.

MAPE is similar to that of MAE, with one key difference, that it calculates error in terms of **percentage**, instead of raw values. Due to this, MAPE is independent of the scale of our variables.

MAPE Equation from JIBC

The following figure shows that the MAPE also increases linearly with an increase in error.

Image by author

- Loss is calculated by normalizing all errors on a common scale (of hundred).

- MAPE equation has the expected output in the denominator, which can be zero. Loss cannot be calculated for these, as division by zero is not defined.
- Again, division operation means that even for the same error, the magnitude of actual value can cause a difference in loss. For example, if the predicted value is 70 and the actual value is 100, the loss would be 0.3 (30%), while for the actual value of 40, the loss would be 0.75 (75%), even though the error in both the cases is the same, i.e. 30.

In MSE, we calculate the square of our error and then take it’s mean. This is a **quadratic scoring** method, meaning, the penalty is proportional to not the error (like in MAE), but to the **square of the error**, which gives relatively higher weight (penalty) to large errors/outliers, while smoothening the gradient for smaller errors.

#machine-learning #loss-function #deep-learning #artificial-intelligence #deep learning

1595573880

In this post, we will investigate how easily we can train a Deep Q-Network (DQN) agent (Mnih et al., 2015) for Atari 2600 games using the Google reinforcement learning library Dopamine. While many RL libraries exist, this library is specifically designed with **four essential features** in mind:

- Easy experimentation
- Flexible development
- Compact and reliable
- Reproducible

_We believe these principles makes _

_Dopamine _one of the. Additionally, we even got the library to work on Windows, which we think isbest RL learning environment available today!quite a feat

In my view, the visualization of any trained RL agent is an **absolute must** in reinforcement learning! Therefore, we will (of course) include this for our own trained agent at the very end!

We will go through all the pieces of code required (which is** minimal compared to other libraries**), but you can also find all scripts needed in the following Github repo.

The general premise of deep reinforcement learning is to

“derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations.”

- Mnih et al. (2015)

As stated earlier, we will implement the *DQN model* by *Deepmind*, which only uses raw pixels and game score as input. The raw pixels are processed using convolutional neural networks similar to image classification. The primary difference lies in the **objective function**, which for the DQN agent is called the *optimal action-value function*

where_ rₜ *is the maximum sum of rewards at time t discounted by γ, obtained using a behavior policy* π = P(a_∣_s)_ for each observation-action pair.

There are relatively many details to Deep Q-Learning, such as *Experience Replay* (Lin, 1993) and an _iterative update rule. _Thus, we refer the reader to the original paper for an excellent walk-through of the mathematical details.

One key benefit of DQN compared to previous approaches at the time (2015) was the ability to outperform existing methods for Atari 2600 games using the **same set of hyperparameters** and **only pixel values and game score as input**, clearly a tremendous achievement.

This post does not include instructions for installing Tensorflow, but we do want to stress that you can use **both the CPU and GPU versions**.

Nevertheless, assuming you are using `Python 3.7.x`

, these are the libraries you need to install (which can all be installed via `pip`

):

```
tensorflow-gpu=1.15 (or tensorflow==1.15 for CPU version)
cmake
dopamine-rl
atari-py
matplotlib
pygame
seaborn
pandas
```

#reinforcement-learning #q-learning #games #machine-learning #deep-learning #deep learning