<?xml version="1.0" encoding="UTF-8" standalone="no"?><rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:blogger="http://schemas.google.com/blogger/2008" xmlns:gd="http://schemas.google.com/g/2005" xmlns:georss="http://www.georss.org/georss" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:openSearch="http://a9.com/-/spec/opensearchrss/1.0/" xmlns:thr="http://purl.org/syndication/thread/1.0" version="2.0"><channel><atom:id>tag:blogger.com,1999:blog-331977333533137262</atom:id><lastBuildDate>Fri, 11 Sep 2026 10:21:00 +0000</lastBuildDate><category>Python Tutorials</category><category>C Programming Tutorial</category><category>Data Science</category><category>data analytics using Power BI</category><category>प्रेरणादायी लेख</category><category>Oracle</category><category>SQL</category><category>AI</category><category>artificial intelligence</category><category>Deep Learning</category><category>प्रेरणादायी</category><category>Machine Learning</category><category>NLP</category><category>BBA(CA). C++ Notes</category><category>Data Analytics using Python</category><category>MBA CET</category><category>MCA CET</category><category>BCA</category><category>BCS</category><category>MCA</category><category>data analysis</category><category>Data Security</category><category>पारंपरिक सण उत्सव</category><category>ML</category><category>कोरोना आणि घडलेले बदल</category><category>ब्लॉग आणि ब्लॉगिंग</category><category>शिक्षक दिन</category><category>शब्द माझे सोबती</category><category>Management</category><category>Project</category><category>शैक्षणिक</category><category>C Programming Notes</category><category>C plus</category><category>C++</category><category>CNN</category><category>Data Analytics Using Tableau</category><category>Ekankika</category><category>GRU</category><category>IT Updates</category><category>Image Classification</category><category>LSTM</category><category>Nested if  else Statement in C Language</category><category>Python</category><category>data visualization</category><category>jagtik mahila din</category><category>marathi articles</category><category>research</category><category>time series forecasting</category><category>transformer</category><category>womens day</category><category>आभार प्रदर्शन</category><category>गुरू पौर्णिमा</category><title>मधूषाब्लॉग्स</title><description>वाचनातून प्रेरणा</description><link>https://madhushablogs.blogspot.com/</link><managingEditor>noreply@blogger.com (Dr.Manisha More)</managingEditor><generator>Blogger</generator><openSearch:totalResults>468</openSearch:totalResults><openSearch:startIndex>1</openSearch:startIndex><openSearch:itemsPerPage>25</openSearch:itemsPerPage><language>en-us</language><itunes:explicit>no</itunes:explicit><itunes:subtitle>वाचनातून प्रेरणा</itunes:subtitle><itunes:owner><itunes:email>noreply@blogger.com</itunes:email></itunes:owner><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-5221882323059164204</guid><pubDate>Wed, 09 Sep 2026 16:12:42 +0000</pubDate><atom:updated>2026-09-09T21:42:42.116+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">time series forecasting</category><category domain="http://www.blogger.com/atom/ns#">transformer</category><title>Transformer-Based Household Electric Power Consumption Forecasting</title><atom:summary type="text">&amp;nbsp;Transformer-Based Household Electric Power Consumption Forecasting
Problem Statement
Develop a Transformer-based time-series forecasting model to predict household electric power consumption using historical electricity usage data. The model will use the previous 60 minutes of Global Active Power consumption to predict the consumption for the next minute. The model's forecasting performance</atom:summary><link>https://madhushablogs.blogspot.com/2026/09/Transformer-Based-Household-Electric-Power-Consumption-Forecasting.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-8348381031067752515</guid><pubDate>Fri, 04 Sep 2026 08:24:43 +0000</pubDate><atom:updated>2026-09-08T12:36:24.370+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">GRU</category><category domain="http://www.blogger.com/atom/ns#">LSTM</category><title>GRU-based Time-Series Forecasting Model to Predict Household Electric Power Consumption</title><atom:summary type="text">GRU-based Time-Series Forecasting Model to Predict Household Electric Power ConsumptionProblem Statement
Develop a GRU-based time-series forecasting model to predict household electric power consumption using historical electricity usage data and evaluate its performance using MAE and RMSE.Download Dataset: Household_Power_Consumption.txtDataset Description
The dataset contains measurements of </atom:summary><link>https://madhushablogs.blogspot.com/2026/09/GRU-based-Time-Series-Forecasting-Model to-Predict-Household-Electric-Power-Consumption.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-7951460309409570076</guid><pubDate>Tue, 01 Sep 2026 06:56:40 +0000</pubDate><atom:updated>2026-09-01T12:26:40.709+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><title>NIFTY 50 Closing Price Prediction Using Long Short-Term Memory (LSTM)</title><atom:summary type="text">&amp;nbsp;NIFTY 50 Closing Price Prediction Using Long Short-Term Memory (LSTM)Problem StatementDevelop an LSTM-based time-series forecasting model to predict the next trading day's NIFTY 50 closing price using historical closing-price data. The model should learn temporal patterns from previous trading days and evaluate its forecasting performance using suitable regression metrics.Dataset NameNIFTY </atom:summary><link>https://madhushablogs.blogspot.com/2026/09/NIFTY-50-Closing-Price-Prediction-Using-Long-Short-Term-Memory-LSTM.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-988225569993790251</guid><pubDate>Tue, 01 Sep 2026 04:12:25 +0000</pubDate><atom:updated>2026-09-02T18:30:20.572+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Long Short-Term Memory (LSTM) Networks</title><atom:summary type="text">Long Short-Term Memory (LSTM) Networks1. IntroductionRecurrent Neural Networks (RNNs) are designed to process sequential or time-series data by remembering information from previous time steps. They work well for short sequences but struggle when the sequence becomes longer.Long Short-Term Memory (LSTM) is an advanced type of RNN that overcomes this limitation by learning what information should </atom:summary><link>https://madhushablogs.blogspot.com/2026/08/Long-Short-Term-Memory-LSTM-Networks.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-5730874380872804942</guid><pubDate>Wed, 26 Aug 2026 05:04:13 +0000</pubDate><atom:updated>2026-08-26T10:34:13.262+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Develop a Simple Recurrent Neural Network (RNN) model to predict the next day's minimum temperature</title><atom:summary type="text">&amp;nbsp;Develop a Simple Recurrent Neural Network (RNN) model to predict the next day's minimum temperatureProblem Statement

Develop a Simple Recurrent Neural Network (RNN) model to predict the next day's minimum temperature using the temperature values of the previous 7 days. Evaluate the model using RMSE and compare actual and predicted temperatures graphically.

Download DatasetDataset </atom:summary><link>https://madhushablogs.blogspot.com/2026/08/Develop-a-Simple-Recurrent-Neural-Network-RNN-model-to-predict-the-next-days-minimum-temperature.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-7655045706365923049</guid><pubDate>Tue, 25 Aug 2026 08:54:36 +0000</pubDate><atom:updated>2026-08-25T14:24:36.373+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><title>RNN Model to Predict Airline Passenger Counts</title><atom:summary type="text">&amp;nbsp;RNN Model to Predict Airline Passenger CountsProblem StatementTo develop a Simple RNN model using the AirTrafficMovement dataset to predict the next month's total passenger traffic based on the previous 12 months' passenger counts.Dataset DescriptionThe AirTrafficMovement dataset contains monthly airport traffic information related to aircraft movements, passenger traffic, air mail, and </atom:summary><link>https://madhushablogs.blogspot.com/2026/08/RNN-Model-to-Predict-Airline-Passenger-Counts.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-94548763172519500</guid><pubDate>Sat, 22 Aug 2026 04:40:50 +0000</pubDate><atom:updated>2026-08-22T10:13:26.025+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><title>Introduction to Optimizers</title><atom:summary type="text">&amp;nbsp;Introduction to Optimizers
In Deep Learning, an optimizer is an algorithm used to update the weights and biases of a neural network to minimize the loss (error) during training.
After Backpropagation calculates the gradients, the optimizer uses these gradients to determine how the weights should be changed.
Training Flow:
Feed Forward → Prediction → Loss → Backpropagation → Gradient → </atom:summary><link>https://madhushablogs.blogspot.com/2026/08/Introduction-to-Optimizers.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>1</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-7481477768804902771</guid><pubDate>Fri, 31 Jul 2026 05:11:23 +0000</pubDate><atom:updated>2026-08-07T14:00:16.333+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">CNN</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Image Classification</category><title>Image Classification Using Convolutional Neural Networks (CNN) with Fashion MNIST Dataset</title><atom:summary type="text">&amp;nbsp;Image Classification Using Convolutional Neural Networks (CNN) with Fashion MNIST DatasetProblem StatementThe objective of this practical is to build a Convolutional Neural Network (CNN) to automatically classify grayscale images of clothing into one of ten fashion categories using the Fashion MNIST dataset.ObjectiveUnderstand the basic architecture of CNN.Load and preprocess the Fashion </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Image-Classification-Using-Convolutional-Neural-Networks-CNN-with-Fashion-MNIST-Dataset.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-6578348387859640248</guid><pubDate>Mon, 27 Jul 2026 04:05:06 +0000</pubDate><atom:updated>2026-07-27T09:35:06.287+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>ANN - for Customer Subscription Prediction Using the Bank Marketing Dataset</title><atom:summary type="text">&amp;nbsp;ANN - for Customer Subscription Prediction Using the Bank Marketing DatasetProblem Statement
Develop an Artificial Neural Network (ANN) model to predict whether a customer will subscribe to a term deposit based on customer demographic, financial, and marketing campaign information.&amp;nbsp;&amp;nbsp;Download DatasetDataset Summary
ParameterValueDataset NameBank Marketing DatasetSourceUCI Machine </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/ann-for-customer-subscription.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-8797652639993510068</guid><pubDate>Sat, 25 Jul 2026 04:22:37 +0000</pubDate><atom:updated>2026-07-25T09:52:37.786+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Diabetes Prediction Using Artificial Neural Network (ANN)</title><atom:summary type="text">Diabetes Prediction Using Artificial Neural Network (ANN)
Problem Statement
Develop an Artificial Neural Network (ANN) model to predict whether a patient is diabetic or non-diabetic using the Pima Indians Diabetes Dataset. The model should be trained using patient health parameters and evaluated using appropriate performance metrics.

Dataset Description
Dataset Name: Pima Indians Diabetes </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Diabetes-Predict-on-Using-Artificial-Neural-Network-ANN.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-1799321321290159786</guid><pubDate>Wed, 22 Jul 2026 05:10:47 +0000</pubDate><atom:updated>2026-07-22T10:43:08.137+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Introduction to CNN and Its Applications in Computer Vision</title><atom:summary type="text">&amp;nbsp;Introduction to CNN and Its Applications in Computer Vision
1. Introduction
Humans can easily recognize objects, faces, animals, vehicles, handwritten text, and different activities in images. For example, when we see an image of a cat, we can identify it even when its position, size, colour, background, or direction changes.
For a computer, an image is not directly understood as a cat, </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Introduction-to-CNN-and-Its-Applications-in-Computer-Vision.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-7432349194335592598</guid><pubDate>Tue, 21 Jul 2026 05:19:48 +0000</pubDate><atom:updated>2026-07-21T10:49:48.235+05:30</atom:updated><title>Deep Feed Forward Neural Network with Backpropagation for Student Placement Prediction</title><atom:summary type="text">&amp;nbsp;Deep Feed Forward Neural Network with Backpropagation for Student Placement Prediction
Problem Statement
Student placement prediction is an important application of Artificial Intelligence and Deep Learning. Educational institutions often need to identify whether a student is likely to be placed based on academic and skill-related factors. Traditional prediction methods rely on manual </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/deep-feed-forward-neural-network-with.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-6781262821615757254</guid><pubDate>Tue, 21 Jul 2026 05:14:08 +0000</pubDate><atom:updated>2026-07-21T13:45:54.713+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title> Stochastic Gradient Descent in Deep Neural Networks</title><atom:summary type="text">&amp;nbsp;Stochastic Gradient Descent in Deep Neural NetworksReal-Life ExampleConsider a hospital where a patient's medical test results, such as radius, texture, perimeter, and area of a breast tumor, are collected. These features are provided as input to the neural network.Input features → Hidden layers → Benign or Malignant prediction


If the model makes an incorrect prediction, the error is </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/ Stochastic-Gradient-Descent-in-Deep-Neural-Networks.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-7804252468746046063</guid><pubDate>Mon, 20 Jul 2026 07:32:13 +0000</pubDate><atom:updated>2026-07-22T21:40:41.658+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Path Finding in a Maze Using the A Search Algorithm</title><atom:summary type="text">&amp;nbsp;Path Finding in a Maze Using the A Search AlgorithmProblem StatementPathfinding is an important Artificial Intelligence problem in which an agent must find the shortest path from a starting position to a goal position while avoiding obstacles.In this practical, the A* Search Algorithm is implemented using Python to solve a pathfinding problem in a two-dimensional maze. A* selects the most </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Path Finding in a Maze Using the-A-star-Search-Algorithm.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-6819381766810289689</guid><pubDate>Fri, 17 Jul 2026 04:04:37 +0000</pubDate><atom:updated>2026-07-17T09:56:53.214+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Feed Forward Neural Network (FFNN) and Backpropagation</title><atom:summary type="text">&amp;nbsp;Feed Forward Neural Network (FFNN) Understanding Information Flow in Artificial Neural Networks
Introduction
In the previous sessions, we learned about Artificial Neural Networks (ANNs), Single-Layer Perceptrons, Multi-Layer Perceptrons, and why hidden layers are required to solve non-linear problems such as XOR and XNOR.
An important question now arises:

How does information actually </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Feed-Forward-Neural-Network-FFNN.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-2667186102911089133</guid><pubDate>Thu, 16 Jul 2026 05:53:33 +0000</pubDate><atom:updated>2026-07-16T11:23:33.832+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Path Finding in a Maze Using Breadth-First Search (BFS) Algorithm </title><atom:summary type="text">&amp;nbsp;Path Finding in a Maze Using Breadth-First Search (BFS) Algorithm&amp;nbsp;Problem Statement
Path finding is a fundamental problem in Artificial Intelligence where an intelligent agent must find a valid path from a starting position to a goal position while avoiding obstacles. In this practical, a maze is represented as a two-dimensional grid, and the Breadth-First Search (BFS) algorithm is </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Path-Finding-in-a-Maze-Using-Breadth-First-Search-BFS-Algorithm .html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-5873920315390810530</guid><pubDate>Wed, 15 Jul 2026 05:10:40 +0000</pubDate><atom:updated>2026-07-15T10:45:17.234+05:30</atom:updated><title>Linear and Non-Linear Problems Using Neural Networks</title><atom:summary type="text">&amp;nbsp;From Single-Layer Perceptron to Multi-Layer Perceptron: Solving Linear and Non-Linear Problems Using Neural NetworksIntroductionArtificial Neural Networks (ANNs) are inspired by the structure and functioning of the human brain. At the core of every ANN lies a simple computational unit called the Perceptron. A perceptron receives inputs, processes them mathematically using weights and bias, </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Linear-and-Non-Linear-Problems-Using-Neural-Networks.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><media:thumbnail xmlns:media="http://search.yahoo.com/mrss/" height="72" url="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi5Uz7wTpy3yldzF80KK4tbWPhJnFzh55STRVZuEEsjiU_NUzdhWDxcMKbOMc4LlTAa5WFuqiTedTy0MjIMcVKbrTKKzo5mlzSlFXANR_vutl0-ZjmI1LzYMnfkA66KY1E5CuShWax229JoAlvSN4EEQGc01aMxwEOuWo08Wr7OVi-Iq5S4IROmHRa3obE3/s72-w400-h153-c/Screenshot%202026-07-15%20104420.png" width="72"/><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-7884544151342459529</guid><pubDate>Tue, 14 Jul 2026 04:58:01 +0000</pubDate><atom:updated>2026-07-15T15:07:18.054+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Understanding the Foundation of Deep Learning</title><atom:summary type="text">&amp;nbsp;Artificial Neural Networks (ANN) Understanding the Foundation of Deep Learning
Artificial Intelligence (AI) has transformed the way machines solve real-world problems. Applications such as ChatGPT, facial recognition, speech assistants, self-driving cars, medical diagnosis, recommendation systems, and fraud detection are all powered by Deep Learning. At the heart of Deep Learning lies one </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Understanding-the-Foundation-of-Deep-Learning.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><media:thumbnail xmlns:media="http://search.yahoo.com/mrss/" height="72" url="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi5gRrEZuEFrek3tYc8hc-vbXTjR95oZhWCtemKzV_hLxOi3ZRttj_NReJ0tFO0W_7I009PKHbwh94tYNfYfS_ZmsF_6NEi440oOsNafXE0_mY4vsaX7dpfpwFf1W5wUcaOUiRjzcbn-59fsF2KnLXg2IAY1oeGCJt1_8lqHkCmrw_2mZDfdAn-NdccaEkV/s72-w400-h152-c/Screenshot%202026-07-14%20104652.png" width="72"/><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-8354803294035600503</guid><pubDate>Mon, 13 Jul 2026 03:58:06 +0000</pubDate><atom:updated>2026-07-13T09:28:06.128+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Search and Reasoning in AI</title><atom:summary type="text">&amp;nbsp;Search and Reasoning in Artificial Intelligence&amp;nbsp;What is Search?
Definition
Search is the process of finding the best or correct solution from multiple possible solutions.
Simple Examples


Finding a file on your laptop


Finding the shortest route in Google Maps


Searching a contact on your phone


AI finding the best chess move


Real-Life Example
Suppose you lost your keys.
You </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Search-and-Reasoning-in-AI.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-4668217287036487047</guid><pubDate>Wed, 08 Jul 2026 04:37:43 +0000</pubDate><atom:updated>2026-07-08T11:14:37.331+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Breast Cancer Prediction Using ANN</title><atom:summary type="text">Breast Cancer Prediction using Artificial Neural Network (ANN)Breast Cancer Prediction :&amp;nbsp;Download Dataset&amp;nbsp;Problem Statement
Breast cancer is one of the most common cancers among women worldwide. Early and accurate diagnosis is essential for timely treatment and improved survival rates. The Breast Cancer Wisconsin Dataset contains various medical features extracted from cell nuclei of </atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Breast-Cancer-Prediction-Using-ANN.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>1</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-4386733479353616940</guid><pubDate>Thu, 02 Jul 2026 08:55:04 +0000</pubDate><atom:updated>2026-07-08T11:56:35.114+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><title>Hotel Booking Prediction Using ANN</title><atom:summary type="text">&amp;nbsp;Hotel Booking Prediction Using ANNDownload Dataset: Hotel Booking DatasetGo Through Jupyter NotebookProblem Statement
The hospitality industry faces significant financial losses due to hotel booking cancellations. By analyzing historical booking data such as booking lead time, customer type, room type, meal plan, market segment, and previous cancellations, an Artificial Neural Network (ANN)</atom:summary><link>https://madhushablogs.blogspot.com/2026/07/Hotel-Booking-Prediction-Using-ANN.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-7830558151506578123</guid><pubDate>Tue, 30 Jun 2026 05:44:23 +0000</pubDate><atom:updated>2026-07-14T09:47:56.939+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">ML</category><title>Introduction to Deep Learning</title><atom:summary type="text">&amp;nbsp;Introduction to Deep Learning1. Introduction&amp;nbsp;Question 1How does your phone recognize your face?Question 2How does ChatGPT answer your questions?Question 3How does YouTube know which video you will watch next?Question 4How does Google Lens identify objects?All these applications are powered by Deep Learning, one of the most influential technologies in Artificial Intelligence today.2. </atom:summary><link>https://madhushablogs.blogspot.com/2026/06/Introduction-to-Deep-Learning.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><media:thumbnail xmlns:media="http://search.yahoo.com/mrss/" height="72" url="https://blogger.googleusercontent.com/img/a/AVvXsEjvlP2MeTqcPVlQvBTnbZwJS8DSnmuiJqtUZtoc5c9c2YYWPY8unobGkMJhkTUmV1FLexdaCLOSBdPB60jqQvj6OJHkq7OzfbEb0GA335duwck2ImcqMwDwOMXykch9Oee6iVqpU5nKFCDk6ufeHUcX7u4EGJ7m16kRWoy_mMsgm2XRrhnp4MtggaJno1Zm=s72-w640-h426-c" width="72"/><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-5086269036806902120</guid><pubDate>Mon, 29 Jun 2026 03:55:04 +0000</pubDate><atom:updated>2026-06-29T09:25:04.272+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">ML</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Classical AI VS Modern AI</title><atom:summary type="text">Introduction to Artificial Intelligence1. What is Intelligence?DefinitionIntelligence is the ability to acquire knowledge, learn from experience, reason logically, solve problems, make decisions, and adapt to new situations.Characteristics of IntelligenceLearning from experienceReasoning and logical thinkingProblem-solvingDecision makingMemory and knowledge retentionPattern </atom:summary><link>https://madhushablogs.blogspot.com/2026/06/Classical-AI-VS-Modern-AI.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-3207319991600818743</guid><pubDate>Sat, 27 Jun 2026 04:23:50 +0000</pubDate><atom:updated>2026-06-27T11:37:03.937+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">artificial intelligence</category><category domain="http://www.blogger.com/atom/ns#">data analysis</category><category domain="http://www.blogger.com/atom/ns#">Data Science</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">ML</category><title>Hotel Booking Prediction Using ML and DL</title><atom:summary type="text">&amp;nbsp;Hotel Booking Prediction Using ML and DLDataset Description
Dataset Name: Hotel Booking Demand Dataset
Description:
The Hotel Booking Demand Dataset contains booking information for City Hotels and Resort Hotels. It includes customer demographics, booking details, stay duration, reservation information, and hotel-related attributes. The dataset is widely used for hotel booking cancellation </atom:summary><link>https://madhushablogs.blogspot.com/2026/06/Hotel-Booking-Prediction-Using-ML-and-DL.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item><item><guid isPermaLink="false">tag:blogger.com,1999:blog-331977333533137262.post-3233096223326461547</guid><pubDate>Tue, 23 Jun 2026 06:07:38 +0000</pubDate><atom:updated>2026-06-24T10:24:52.198+05:30</atom:updated><category domain="http://www.blogger.com/atom/ns#">AI</category><category domain="http://www.blogger.com/atom/ns#">Deep Learning</category><category domain="http://www.blogger.com/atom/ns#">Machine Learning</category><category domain="http://www.blogger.com/atom/ns#">ML</category><category domain="http://www.blogger.com/atom/ns#">NLP</category><title>Introduction to Artificial Intelligence, ML, DL and NLP</title><atom:summary type="text">&amp;nbsp;Introduction to Artificial Intelligence, Machine Learning, Deep Learning and Natural Language Processing1. Ice Breaker&amp;nbsp;How many of you use ChatGPT?How does Instagram recommend reels?How does Google Maps predict traffic?How does Face Unlock work?How does Alexa understand your voice?All these technologies are powered by Artificial Intelligence, Machine Learning, Deep Learning and Natural</atom:summary><link>https://madhushablogs.blogspot.com/2026/06/Introduction-to-Artificial-Intelligence-ML-DL-and-NLP.html</link><author>noreply@blogger.com (Dr.Manisha More)</author><thr:total>0</thr:total></item></channel></rss>