Deep Learning
Pfam protein sequence classification
Classifying given protein sequence of amino acid to one of the family accession. This model can be used for prediction of a given protein sequence of amino acid. The model will generate a number of classes probability values corresponding to the number of class or family accession. The highest probability value to the corresponding class will be the predicted class for that protein sequence of amino acid.
Alogorithm Used: Neural Network.
Technologies Used: Python,Pandas,Scikit-Learn,keras,Flask.
Published Article: Pfam protein sequence classification
Human Activity Recognition
Domain experts from the field of Signal Processing collects the data from Accelerometer and Gyroscope of Smartphone. They break up the data in the time window of 2.56 seconds with 50% overlapping i.e., 128 reading.They engineered 561 features from each time window of 2.56 seconds.By using either human engineered 561 feature data or raw features of 128 reading, our goal is to predict one of the six activities that a Smartphone user is performing at that 2.56 Seconds time window
Alogorithm Used: Neural Network.
Technologies Used: Python,Pandas,Scikit-Learn,keras,Flask.
Self Driving Car
We are here building a minimal version of self driving car. Here, we have a front camera view. This will transfer input to the computer. Then Deep Learning algorithm in computer predicts the steering angle to avoid all sorts of collisions. Predicting steering angle can be thought of as a regression problem. We will feed images to Convolutional Neural Network and the label will be the steering angle in that image. Model will learn the steering angle from the as per the turns in the image and will finally predicts steering angle for unknown images.
Alogorithm Used: Neural Network.
Technologies Used: Python,Pandas,Scikit-Learn,keras,tensorflow,Flask.
Music Generation Using Deep learning
Generating music from input using deep learning
Alogorithm Used: Neural Network.
Technologies Used: Python,Pandas,Scikit-Learn,keras,Flask.
MOOCS
Machine Learning Course From Applied Ai Course
This course provides a broad introduction to machine learning,deep learning, and statistical pattern recognition.
Topics include:
(i) Supervised learning (parametric/non-parametric algorithms,KNN,Naive Bayes,Linear Regression,Logistic Regression, support vector machines, kernels,Decsions tree,Ensembe Modeling, Neural networks,CNN,RNN,LSTM).
(ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning).
(iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI).
The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.
