Professional Documents
Culture Documents
Unit-2 Adl
Unit-2 Adl
Unit-2 Adl
Residual Network
Intro-
Deep Neural Networks are becoming deeper and more complex. It has been proved
that adding more layers to a Neural Network can make it more robust for
image-related tasks. But it can also cause them to lose accuracy. That’s where
Residual Networks come into place.
The advantage of adding this type of skip connection is that if any layer hurt
the performance of architecture then it will be skipped by regularization. So,
this results in training a very deep neural network without the problems
caused by vanishing/exploding gradient.
.
Skip Connections (or Shortcut Connections) as the name suggests skips some of the layers
in the neural network and feeds the output of one layer as the input to the next layers.
Skip Connections were introduced to solve different problems in different
architectures. In the case of ResNets, skip connections solved the degradation
problem that we addressed earlier whereas, in the case of DenseNets, it ensured
feature reusability.
2.desnet
The idea behind the concatenation is to use features that are learned from
earlier layers in deeper layers as well. This concept is known as Feature
Reusability. So, DenseNets can learn mapping with fewer parameters than
a traditional CNN as there is no need to learn redundant maps.
Image denoising is the process of removing noise from images. Deep learning has
revolutionized this field by offering powerful techniques that can achieve impressive
This noise can come in various forms, like Gaussian noise (random variations in
Noise makes images appear grainy, blurry, or distorted, reducing their quality and
usefulness.
Traditional Denoising Methods
These methods can be effective for certain types of noise, but they may struggle to
emerged as powerful tools for image denoising. Here's how they work:
large datasets of noisy and clean image pairs. The model learns to identify the
noise patterns in the noisy image and map it to the corresponding clean
image.
capture both high-level and low-level details, allowing for better noise removal
filters.
○ Preserving Image Details: Deep learning models can be trained to
remove noise while preserving important image details like edges and
textures.
fields, including:
and diagnosis.
Overall, deep learning has become a powerful tool for image denoising, offering
expect even more sophisticated models that can achieve even better denoising
performance.
SEMANTIC SEGMENTATION
R-CNN
Architecture
R-CNN (Regions with CNN feature) is one representative work for the
region-based methods. It performs the semantic segmentation based
on the object detection results. To be specific, R-CNN first utilizes
selective search to extract a large quantity of object proposals and
then computes CNN features for each of them. Finally, it classifies
each region using the class-specific linear SVMs. Compared with
traditional CNN structures which are mainly intended for image
classification, R-CNN can address more complicated tasks, such as
object detection and image segmentation, and it even becomes one
important basis for both fields. Moreover, R-CNN can be built on top of
any CNN benchmark structures, such as AlexNet, VGG, GoogLeNet,
and ResNet.
FCN
Architecture
One issue in this specific FCN is that by propagating through several
alternated convolutional and pooling layers, the resolution of the
output feature maps is down sampled. Therefore, the direct
predictions of FCN are typically in low resolution, resulting in relatively
fuzzy object boundaries. A variety of more advanced FCN-based
approaches have been proposed to address this issue, including
SegNet, DeepLab-CRF, and Dilated Convolutions.
Boxsup
Training
Object Detection
Object detection with deep learning is a powerful technique for identifying and
locating objects within images and videos. It's a crucial component in many computer
vision applications like self-driving cars, facial recognition, and medical image
analysis.
● Two-Stage Detectors:
○ This approach involves two stages: a region proposal stage and a
classification stage.
○ In the first stage, the model proposes candidate regions where objects
might be present.
○ Then, in the second stage, the model classifies these proposed regions
and refines the bounding boxes around the objects.
○ Examples of two-stage detectors include R-CNN (Regions with CNN
features) and its variants like Fast R-CNN and Faster R-CNN.
● Single-Stage Detectors:
○ This approach is faster and simpler than two-stage detectors.
○ The model directly predicts bounding boxes and class labels for objects
in a single step.
○ Single-stage detectors are often preferred for real-time applications
due to their speed.
○ Popular single-stage detectors include YOLO (You Only Look Once)
and SSD (Single Shot MultiBox Detector).
-High Accuracy
-Real-Time Capability
-Adaptability
particularly for tasks involving sequences like natural language processing (NLP)
and computer vision. Here's a breakdown of what they are and how they
● Unlike traditional deep learning models that process all parts of the input data
equally, attention models allow the network to focus on specific, relevant parts
of the input.
● This is similar to how humans focus their attention when reading a sentence
or looking at a scene. We don't pay equal attention to every word or detail, but
rather prioritize the information that's most important for understanding the
context.
There are different ways to implement attention mechanisms, but the core idea
1. Calculating Scores: The model assigns a score to each element in the input
sequence. This score reflects how relevant that element is to the current
processing step.
each element.
of the elements in the input sequence, using the attention weights calculated
While initially developed for sequential data, attention mechanisms are being
● Visual Question Answering: Attention can help models focus on relevant parts
Overall, attention models have become a powerful tool in deep learning, allowing
models to focus on the most critical information and achieve superior performance
● Encoder: This part takes the source language sentence as input and
● Decoder: The decoder takes the encoded representation from the encoder
and generates the target language sentence word by word. During this
process, the decoder might attend back to the source sentence encoded by
NMT models are trained on massive datasets of text that have already been
translated by humans. These datasets serve as a reference for the model to learn
another.
● Ability to Learn New Languages: NMT models can be relatively easily adapted
datasets.
resources.
more accurate and natural way to bridge the language gap. As NMT models
continue to develop and training data becomes more available, we can expect even
BASELINE METHODS
evaluate the performance of more complex models. They serve as a reference point
Here's a deeper dive into what baseline models are and why they're important:
Imagine you're developing a new deep learning model for image classification. You
train the model and achieve a certain level of accuracy. But is this accuracy good?
Without a baseline for comparison, it's difficult to assess how well your model is
model on the same task and data, you create a reference point. You can then
compare the performance of your new model to the baseline. If your model
effective.
simple model achieves high accuracy, it suggests that the task itself might be
simpler approaches, you can focus your efforts on developing models that can
● Random Guessing: This is the simplest baseline, where the model randomly
predicts a class label or output for each input. The accuracy of random
predicts the most frequent class in the training data. This is a good starting
point to see how well a model can learn to differentiate between classes
models capture basic linear relationships in the data and provide a benchmark
models can capture some underlying patterns in the data and serve as a
The best type of baseline model depends on the specific task and the complexity of
development workflow, you can gain valuable insights into your data, manage
expectations, and ultimately build more powerful and efficient deep learning models.
DATA REQUIREMENTS
Data is the fuel that drives deep learning models. The amount of data you need
depends on several factors, but it's generally true that deep learning models require
a breakdown of why data is so crucial and how much you might need:
Deep learning models have complex architectures with many parameters. These
parameters act like learnable filters that extract patterns from the data. The more
data you have, the better the model can learn these patterns and generalize well to
unseen examples.
● High Capacity for Complex Patterns: Deep learning models can learn very
complex patterns from data. However, this also means they are prone to
overfitting if they don't have enough data to learn from. Overfitting happens
when the model memorizes the training data too well and fails to perform well
on new data.
data. With more data, these patterns become more statistically robust, leading
There's no one-size-fits-all answer to how much data you need. Here are some
factors to consider:
● Task Difficulty: More complex tasks like image recognition with fine-grained
details might require more data than simpler tasks like sentiment analysis.
very simple tasks or as a starting point for transfer learning (using pre-trained
range for many deep learning tasks, especially with careful model design and
data).
● Large Datasets (Millions-Billions of data points): These are often used for
very complex tasks like image recognition with millions of categories or large
large dataset and fine-tune them for your specific task with less data.
● Data Augmentation: Artificially create more data from your existing dataset
through techniques like cropping, flipping, or adding noise. This can help
● Active Learning: This approach focuses on acquiring data points that are
Conclusion
Data is a critical element for deep learning success. While the amount of data
required can vary greatly depending on the specific task and model, it's safe to say
that deep learning models are data-hungry. By understanding the role of data and
employing techniques to mitigate scarcity, you can effectively train deep learning
HYPERPARAMETER TUNING
learning process of the model, but unlike regular parameters, they are not learned