Scribd
Upload
15 views

AI with python

Uploaded by

nikhileshvarma2002
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
15 views

AI with python

Uploaded by

nikhileshvarma2002
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

Review

Artificial Intelligence with python


Subject: Industrial Internship(19ECS493)
Mentor:Mr.Pravin Mundhe
Nikhilesh Varma Rudraraju
222010313006
Introduction
❖ Machine learning and deep learning, as one of the most prominent fields of today are
quickly in improving many aspects of our life.

❖ One of the categories that provide the strongest results in resolving real-world problems is
Convolutional Neural Networks (CNN).
Artificial Intelligence
● Artificial Intelligence (AI) refers to the ability of computers or machines to perform tasks that
typically require human intelligence. These tasks can include things like understanding and
processing natural language, recognizing patterns in data, making decisions, and solving
problems

● Artificial intelligence with python : Artificial Intelligence (AI) with Python involves using the
Python programming language to build and work with AI systems. Python is a popular
programming language that's well-suited for AI development because of its simplicity and a wide
range of libraries and tools available for machine learning, data analysis, and AI applications.
Machine Learning
Machine learning is a type of technology that allows computers to learn from
data and make decisions or predictions without being explicitly programmed to do
so.
Types of learning algorithms:
1.Supervised:In supervised learning, the algorithm is trained on a labeled dataset, where
the input data is paired with the corresponding correct output or target.
2.Unsupervised:Unsupervised learning algorithms work with unlabeled data, trying to
identify patterns or structure within the data.
3.Semi-supervised: Semi-supervised learning combines elements of both supervised and
unsupervised learning. It uses a small amount of labeled data and a larger amount of
unlabeled data.
PROJECT- Fashion MNIST Classification

The Fashion-MNIST dataset was created to pose a more challenging classification task than
the simple MNIST digits data, which saw performance reaching upwards of 99.7%. The
dataset contains 70,000 28x28 grayscale images of fashion products from 10 categories
from a dataset of Zalando article images, with 7,000 images per category. The training set
consists of 60,000 images and the test set consists of 10,000 images. The dataset is widely
used for learning and practicing how to develop, evaluate, and use deep convolutional
neural networks for image classification from scratch Fashion MNIST data classification
primarily uses Convolutional Neural Networks (CNNs) for image classification. CNNs are
deep learning models that are designed to process data with a grid-like topology, such as
images.
Steps Involved

1. Data set Loading


2. Model Construction
3. Model Training
4. Model Analysis
5. Image Testing
Classification
● we use Convolutional Neural Network (CNN) which is the best
model for Fashion MNIST classification
● CNN is commonly used in computer vision, Computer vision is

a field of AI that enables the computer to understand and


interpret image or visual data
● CNN is an extended version of Artificial Neural Network (ANN)

which is predominantly used to extract the feature from the grid-like


matrix dataset
Implementation and Sample code
Output
Conclusion

● The main objective is to compare the results of various machine learning models and
algorithms and choose the best model based on performance measures/scores.
● With the growth in deep learning methodologies, image recognition using CNN is
excessively applied in fashion domains such as clothes classification, clothes
retrieval ,automatic clothes labeling and fashion recommendation systems for
improving online shopping experience
References

1. Hu, W., Huang, Y., Wei, L., Zhang, F., & Li, H. (2015). Deep convolutional neural
networks for hyper spectral image classification. Journal of Sensors, 2015.
2. Alom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M. S., & Asari, V.
K. (2019). A state-ofthe-art survey on deep learning theory and architectures.
Electronics, 8(3), 292.
3. github, (2019), https://github.com/zalandoresearch/fashionmnist, Accessed: April,
2019.
THANK YOU..

You might also like