DeepLearning-NeuralNet-ComputerVision-ImageProcessing Neural Network: Digit Recognizer (Kaggle MNIST dataset) Dataset: https://www.kaggle.com/c/digit-recognizer 1. Cross Entropy Loss using Logistic Regression for Single-Layer NN as a Benchmark Final error rate: $0.08$ Visual Perception Autonomous Driving: 1. Stereo Depth to Driving Scenario Closest point depth (meters): $28.92655372619629$ 2. Visual Odometry for Localization in Autonomous Driving Figure: Camera Trajectory(3D Visualization) 3. Environment Perception For Self Driving Cars Figure: Estimate distance to impact 4. Mission Planning Dijkstras & A* search Algorithm Computer Vision (Kaggle): Convolutional Classifier after 30 epochs: val_loss: 0.3322, val_binary_accuracy: 0.8620
