Scribd
Upload
32 views2 pages

Assissement 18

Uploaded by

Rohan Ashish
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
32 views2 pages

Assissement 18

Uploaded by

Rohan Ashish
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Ques -1-: Write about Evolution of AI,Ml and DL

Ans-: Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) have
evolved significantly over the past few decades. Here's a brief overview of their evolution:
Artificial Intelligence (AI):
The concept of AI was first proposed in the 1950s. It started with the development of expert
systems, which were designed to solve complex problems using a set of rules. However,
these systems had limitations and were not able to adapt to new situations or learn from
experience. In the 1980s, the concept of neural networks was introduced, which opened up
new avenues for AI research.
Machine Learning (ML):
Machine Learning, a subset of AI, came into existence in the 1990s. The primary focus of
ML was to enable machines to learn from data and improve their performance over time. This
was achieved through algorithms that could automatically identify patterns and relationships
in data.
Deep Learning (DL):
Deep Learning, a subset of ML, was introduced in the early 2000s. The primary focus of DL
was to create artificial neural networks that could learn and solve complex problems. Deep
Learning algorithms are designed to recognize patterns in large sets of data and perform tasks
like image and speech recognition. Over the past decade, DL has gained tremendous
popularity due to its ability to solve complex problems with high accuracy. This has been
made possible by the availability of large amounts of data and powerful computing resources.
DL has enabled significant advancements in areas such as natural language processing, image
recognition, and autonomous vehicles. In summary, the evolution of AI, ML, and DL has
been driven by advancements in computing power, data availability, and algorithmic
innovations. With the rapid pace of technological advancements, it is exciting to see what the
future holds for these fields.
Que-2-: How DL works at neuron Level.
Ans-: Deep learning is a subfield of machine learning that is inspired by the structure and
function of the human brain. Deep learning models are typically composed of artificial
neurons that are organized into layers, and these layers are interconnected to form a neural
network. At the most basic level, a neuron in a neural network receives input from other
neurons, processes that input, and then produces output that is passed to other neurons. At the
neuron level, the input to a neuron is typically a vector of numerical values that represent the
output of other neurons in the previous layer of the neural network. Each input value is
multiplied by a weight, which represents the strength of the connection between the two
neurons. The neuron then sums up all the weighted inputs and adds a bias term, which
represents the neuron's threshold for activation. The summed value is then passed through an
activation function, which introduces nonlinearity into the output of the neuron. The most
commonly used activation function is the rectified linear unit (ReLU), which simply returns
the input if it is positive and zero otherwise. Other activation functions include the sigmoid
function, which squashes the output of the neuron to a value between 0 and 1, and the
hyperbolic tangent function, which squashes the output of the neuron to a value between -1
and 1. The output of the neuron is then passed to other neurons in the next layer of the neural
network, where the process is repeated. The weights and biases of the neurons are updated
during training using an optimization algorithm, such as stochastic gradient descent, to
minimize a loss function that measures the difference between the predicted output of the
neural network and the actual output. In summary, deep learning works at the neuron level by
processing input from other neurons, applying weights and biases to that input, passing the
result through an activation function, and producing output that is passed to other neurons in
the network. By adjusting the weights and biases during training, the neural network can
learn to make accurate predictions for a given task.
Ques-3-: Write merits and Applications of DL
Ans-: Deep Learning (DL) is a subset of Artificial Intelligence that uses neural networks to
model and solve complex problems. Some of the merits and applications of DL include:
Merits:
 Deep learning algorithms can learn and adapt to new data inputs, making them
flexible and scalable.
 DL can handle large amounts of unstructured data such as images, videos, and audio,
making it well suited for applications such as computer vision and speech recognition.
 It can perform feature extraction and selection automatically, eliminating the need for
manual feature engineering, and saving time.
 DL can identify patterns and trends in data that humans might not be able to detect,
enabling more accurate predictions and decision-making.
 It is capable of solving complex problems that traditional machine learning algorithms
cannot.
Applications:
 Computer vision: DL is used to analyse and understand images and videos, making it
valuable for applications such as facial recognition, object detection, and autonomous
vehicles.
 Natural language processing: DL is used to improve speech recognition, language
translation, and language generation.
 Healthcare: DL is used to analyse medical images such as MRI and CT scans to
identify and diagnose diseases.
 Financial services: DL is used to detect fraud, forecast market trends, and assess risk
in lending.
 Robotics: DL is used to control robotic systems and enable them to perform complex
tasks autonomously.
 These are just a few examples of the many applications and merits of DL. As the field
of AI continues to advance, DL is likely to play an increasingly important role in
many industries and domains.

You might also like