• Grade: 100%

• Coursera Certificate

• Implementations:

  1. 1. Linear Regression and Logistic Regression

     2. One-vs-all Logistic Regression

     3. Back propagation algorithm for Neural Networks to recognize hand-written digits

     4. Regularized Linear Regression with bias-variance properties

     5. Support Vector Machine (SVM) to build an email spam classifier

     6. K-means clustering algorithm to compress an image

     7. Principal Component Analysis to find a low-dimensional representation of face images

     8. Anomaly detection algorithm to detect failing servers on a network

     9. Collaborative filtering to build a movie recommendation system

• Coursera Certificate

• Implementations:

  1. 1. Logistic Regression Classifier to recognize cats

     2. Two-layer Neural Network (with a single hidden layer)

     3. Deep Neural Network to build a cat classifier

• Grade: 100%

• Coursera Certificate

• Implementations:

  1. 1. Regularization in deep learning models (L2 regularization, Dropout)

     2. N-dimensional Gradient Checking

     3. Mini-batch Gradient Descent with Momentum

     4. Adam Optimization algorithm for training Neural Networks

• Grade: 100%

• Coursera Certificate

• Implementations:

  1. 1. Forward propagation for the basic Recurrent Neural Network (RNN) and LSTM using NumPy.

     2. Back propagation in RNNs using NumPy.

     3. Character level language model to make new dinosaur breeds names with gradient clipping, sampling using NumPy.

     4. LSTM network to improvise jazz music using NumPy.

     5. Word similarity using cosine similarity function.

     6. Word embeddings to solve word analogy problem.

     7. Emojifier using word vector representations in NumPy and LSTM in Keras.

     8. Neural Machine Translation (NMT) model to translate human-readable dates into machine-readable dates using Attention Model in Keras.

     9. Trigger word detection from speech dataset using Keras.

• Grade: 100%

• Coursera Certificate

• Implementations:

  1. 1. Convolutional Neural Network (implemented convolutional and pooling layers with both forward propagation and backward propagation)

     2. Convolutional Neural Network using TensorFlow to build a sign language detection model

     3. Convolutional Neural Network using Keras to build an emotion detection model.

     4. Residual Networks (ResNets) blocks using Keras to implement and train a state-of-the-art neural network for image classification

     5. You Only Look Once (YOLO) algorithm to build a car detection model.

     6. Neural Style Transfer algorithm with transfer learning on VGG model.

     7. Face recognition system using triplet loss function and a pretrained model to map face encodings.

• Grade: 100%

• Coursera Certificate

• Knowledge gained:

  1. 1. Train/dev/test set distributions

     2. High bias/variance problem

     3. Transfer Learning and Multi-task Learning

     4. End-to-end Deep Learning

     5. Case study (Bird recognition and Autonomous Driving)

• Grade: 100%

• Coursera Certificate

• IBM Badge

• Knowledge gained:

  1. 1. Python basics (types, expressions and variables, string operations)

     2. Python data structures (tuples and list, dictionaries, sets)

     3. Python programming fundamentals (conditions and branching, loops, functions, objects and classes)

     4. Working with data in python (reading and writing files using open function)

     5. Working on datasets using Pandas and Numpy

     6. Web scraping with Python to build a Fake Album Cover Game

• Grade: 100%

• Coursera Certificate

• IBM Badge

• Knowledge gained:

Importing datasets (understanding the data, basic insights of dataset, accessing dataset, DB-API)

Data wrangling (preprocessing data, dealing with missing values, data formatting, data normalization, data binning, one-hot encoding)

Exploratory data analysis (descriptive statistics of data, data grouping, correlation, analysis of variance)

Model development (linear regression, multiple linear regression, polynomial regression, pipeline, in-sample evaluation measurement, model evaluation using visualization, prediction and decision making)

Model evaluation (generalization error, cross validation, ridge regression, grid search)

• Grade: 100%

• Coursera Certificate

• IBM Badge

• Knowledge gained:

  1. Data visualization tools (basic plotting with matplotlib, line plots)

  2. Basic visualization tools (area plots, histograms, bar charts)

  3. Specialized visualization tools (pie charts, box plots, scatter plots)

  4. Advanced visualization tools (waffle charts, word clouds, seaborn and regression plots)

  5. Visualizing geospatial data (folium, choropleth maps)

• Grade: 100%

• Coursera Certificate

• Knowledge gained:

  1. Real-life roles and responsibilities of a junior data analyst

  2. How businesses transform data into actionable insights

  3. Spreadsheet, database, and query basics

  4. Data visualization basics

• Skillsets:

  1. Using data in everyday life

  2. Thinking analytically

  3. Applying tools from the data analytics toolkit

  4. Showing trends and patterns with data visualizations

  5. Ensuring fair data analysis