Javed's repositories
Data-Science
Data Science in Python : Matplotlib, Scikit-learn, Numpy, Pandas
Ethereum-Voting-Dapp
We'll build a client-side application that will talk to our smart contract on the blockchain. This client-side application will have a table of candidates that lists each candidate's id, name, and vote count. It will have a form where we can cast a vote for our desired candidate. It also shows the account we're connected to the blockchain with under "your account". Installing Dependencie
google-translate-api
A free and unlimited API for Google Translate :dollar::no_entry_sign:
GUI_Tkinter
A GUI application to get weather
Natural-Language-Processing
Natural Language Processing (NLP) uses algorithms to understand and manipulate human language. This technology is one of the most broadly applied areas of machine learning. As AI continues to expand, so will the demand for professionals skilled at building models that analyze speech and language, uncover contextual patterns, and produce insights from text and audio. This Specialization will equip you with the state-of-the-art deep learning techniques needed to build cutting-edge NLP systems. By the end of this Specialization, you will be ready to design NLP applications that perform question-answering and sentiment analysis, create tools to translate languages and summarize text, and even build chatbots. This Specialization is for students of machine learning or artificial intelligence as well as software engineers looking for a deeper understanding of how NLP models work and how to apply them. Learners should have a working knowledge of machine learning, intermediate Python including experience with a deep learning framework (e.g., TensorFlow, Keras), as well as proficiency in calculus, linear algebra, and statistics. If you would like to brush up on these skills, we recommend the Deep Learning Specialization, offered by deeplearning.ai and taught by Andrew Ng. This Specialization is designed and taught by two experts in NLP, machine learning, and deep learning. Younes Bensouda Mourri is an Instructor of AI at Stanford University who also helped build the Deep Learning Specialization. Łukasz Kaiser is a Staff Research Scientist at Google Brain and the co-author of Tensorflow, the Tensor2Tensor and Trax libraries, and the Transformer paper.
PongpygameKNeighborsRegressor
Creating a simple Pong-like game in Python, using the PyGame library.
Android-Based-Optical-Character-Recognition
Nowadays, almost everything is digital. Books, newspapers, articles – name it. So what can be done to make a written or printed text digitized or even translated? Optical Character Recognition (OCR) comes with the solution. It’s capable of finding the text on the images and making it digital. This android based OCR will allow user to snap or capture image using phone camera and then detect text in image. It uses Firebase MLKit for text recognition.
SPAM-HAM-DETECTION---Naive-Bayes-classifier
Naive Bayes classifiers are a collection of classification algorithms based on Bayes' Theorem. It is not a single algorithm but a family of algorithms where all of them share a common principle, i.e. every pair of features being classified is independent of each other.
BuildingMarksheet-HTML
Building a Sem-III Marksheet
CanvasResume
Simple Resume Design inspired by Canva designs using HTML and CSS
Deep-Learning-OCR
We will create a simple neural network, known as a perceptron, to classify handwritten digits into ‘five’ or ‘not five’. This is known as optical character recognition. MNIST: Modified National Institute of Standards and Technology . Perceptrons take in an array of numbers - in this case pixel values - and output a single number. The output will be a 1 if the digit is a five, and 0 if it is any other number. We train perceptrons with training data, which are the handwritten digits labelled with what number they are. Perceptrons weight each of the input numbers to reach a correct classification. For instance, if we start with random weights and train our model with some data that it knows is a five, it will adjust how much it weights each of pixels depending on how predictive they are. This may mess up the weights for the earlier data but we don't worry about that now. Running through all of the data once and adjusting these weights is known as completing one epoch. After one epoch, we will have an initial guess at the weights for each pixel. We can then run through all of the data again and again, fine tuning the weights each time. Finally, we take the weighted sum of the pixel values to create an output number. We can interpret the output however we want: in this case anything greater than 0 means that it is a 5. Understanding the code How do we transfer our intuition to code? We use the popular Machine Learning library Keras to create our model in just 30 lines of code. We feed this model some training data, but hold out a portion as validation data. This is used to test our model later, to make sure that the model hasn’t just learnt the training data (known as overfitting) and can generalize to new data too. In order to find the model with the best weights, keras uses backpropagation. Backpropagation means that when the model adjusts the weights based on new inputs, it calculates how it would have affected the previous data that it has seen. This is the intuition for gradient descent. There are different ways to calculate loss, known as loss functions. In this section we use Mean Squared Error (MSE). Another parameter we define in our model is the learning rate. This determines how fast we adjust (or ‘learn’) weights in response to seeing new data. If this rate is too slow, it will take too long to learn the optimal weights. However, if the rate is too fast we may skip over the optimal weights. The best choice of learning rate depends on the exact problem, and is a focus of machine learning research.
IoT-Data-Integration-and-Visualization
In this project, I designed and implemented an end-to-end IoT data processing and visualization solution using a stack of AWS services. The primary objective was to seamlessly collect, process, and gain actionable insights from IoT sensor data, ultimately improving operational efficiency
SPELL-CORRECTOR
A regular expression is a special sequence of characters that helps you match or find other strings or sets of strings, using a specialized syntax held in a pattern.
Users-System-Using-HTML-PHP-Mysql
create a user system using HTML & PHP MySQL