Pinned Repositories
Deep_Learning_Specialization-By-DeepLearning.AI-Coursera
The Deep Learning Specialization is a foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. In this Specialization, you will build and train neural network architectures such as Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, Transformers, and learn how to make them better with strategies such as Dropout, BatchNorm, Xavier/He initialization, and more. Get ready to master theoretical concepts and their industry applications using Python and TensorFlow and tackle real-world cases such as speech recognition, music synthesis, chatbots, machine translation, natural language processing, and more. AI is transforming many industries. The Deep Learning Specialization provides a pathway for you to take the definitive step in the world of AI by helping you gain the knowledge and skills to level up your career. Along the way, you will also get career advice from deep learning experts from industry and academia.
Fundamentals-of-Reinforcement-Learning
Generative-Adversarial-Networks-GANs-Specialization-By-DeepLearning.AI-Coursera
The DeepLearning.AI Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques through an easy-to-understand approach. It also covers social implications, including bias in ML and the ways to detect it, privacy preservation, and more.
gym-flp
Implements different discrete and continuous Facility Layout Problem representations
Kalman-Filters
Filtering Robots perceive the world through sensors, but sensors are inherently noisy making it challenging to observe environmental states completely. There is advance understanding of physical systems like kinematics and dynamics of different robots. This knowledge can provide state estimates, but mathematical models too are not perfect. The problem is as follows, given noisy sensor measurements and knowledge of the system, how to combine this information such that the results is better than the individual results. A well-known solution to this problem is the use of filter algorithms to suppress sensor noise and or fuse multiple sensors for a better state estimate. There are many filters, but the famous ones in robotics are kalman filter, complementary filter, low-pass filter, band-pass filter and high-pass filter. Although named differently, all these filters share a common foundation. Here, we will derive a generic filter.
Kinematics-of-Mobile-Robot
Kinematics is the most basic study of how mechanical systems behave. In mobile robotics, we need to understand the mechanical behavior of robots both in order to design appropriate mobile robots for tasks and to understand how to create control software for an instance of mobile robot hardware. In this task, you will derive the inverse kinematic model of a four-wheeled omnidirectional robot shown in Figure 1, design a position controller and test it on the provided virtual experiments. The task requires v-rep (for visualization) and Matlab (coding) tools.
Localization
1.Pioneer Odometry An encoder attached to each wheel of the differential drive robot gives the angle range from [-π, π]. For a robot performing rolling motion, it rotates about a point that lies along their common left and right wheel axis. The point that the robot rotates is called ICC (Instantaneous Center of Curvature), Figure 1. The given parameters of the robot; Wheel radius (r) = 𝑑2 = 0.0975m and Wheel Track (T) = 0.3310m Figure 1 Differential Drive Kinematics Figure
Object-Localization-with-Tensorflow---Coursera
In this course, our primary learning objective is to create and train a multi output convolutional neural network to perform object localization. We will also learn to create custom callbacks and custom metrics in Keras.
Perception
Perception is the process by which robots map sensor measurements into internal representation of their environment. This internal representation is a task-oriented knowledge representation upon which to control, make decision and plan actions.
ROS_Catkin_WS
DIY ROS Projects
Shimraz's Repositories
Shimraz/Deep_Learning_Specialization-By-DeepLearning.AI-Coursera
The Deep Learning Specialization is a foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. In this Specialization, you will build and train neural network architectures such as Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, Transformers, and learn how to make them better with strategies such as Dropout, BatchNorm, Xavier/He initialization, and more. Get ready to master theoretical concepts and their industry applications using Python and TensorFlow and tackle real-world cases such as speech recognition, music synthesis, chatbots, machine translation, natural language processing, and more. AI is transforming many industries. The Deep Learning Specialization provides a pathway for you to take the definitive step in the world of AI by helping you gain the knowledge and skills to level up your career. Along the way, you will also get career advice from deep learning experts from industry and academia.
Shimraz/Perception
Perception is the process by which robots map sensor measurements into internal representation of their environment. This internal representation is a task-oriented knowledge representation upon which to control, make decision and plan actions.
Shimraz/Generative-Adversarial-Networks-GANs-Specialization-By-DeepLearning.AI-Coursera
The DeepLearning.AI Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques through an easy-to-understand approach. It also covers social implications, including bias in ML and the ways to detect it, privacy preservation, and more.
Shimraz/Kinematics-of-Mobile-Robot
Kinematics is the most basic study of how mechanical systems behave. In mobile robotics, we need to understand the mechanical behavior of robots both in order to design appropriate mobile robots for tasks and to understand how to create control software for an instance of mobile robot hardware. In this task, you will derive the inverse kinematic model of a four-wheeled omnidirectional robot shown in Figure 1, design a position controller and test it on the provided virtual experiments. The task requires v-rep (for visualization) and Matlab (coding) tools.
Shimraz/Localization
1.Pioneer Odometry An encoder attached to each wheel of the differential drive robot gives the angle range from [-π, π]. For a robot performing rolling motion, it rotates about a point that lies along their common left and right wheel axis. The point that the robot rotates is called ICC (Instantaneous Center of Curvature), Figure 1. The given parameters of the robot; Wheel radius (r) = 𝑑2 = 0.0975m and Wheel Track (T) = 0.3310m Figure 1 Differential Drive Kinematics Figure
Shimraz/Fundamentals-of-Reinforcement-Learning
Shimraz/gym-flp
Implements different discrete and continuous Facility Layout Problem representations
Shimraz/Kalman-Filters
Filtering Robots perceive the world through sensors, but sensors are inherently noisy making it challenging to observe environmental states completely. There is advance understanding of physical systems like kinematics and dynamics of different robots. This knowledge can provide state estimates, but mathematical models too are not perfect. The problem is as follows, given noisy sensor measurements and knowledge of the system, how to combine this information such that the results is better than the individual results. A well-known solution to this problem is the use of filter algorithms to suppress sensor noise and or fuse multiple sensors for a better state estimate. There are many filters, but the famous ones in robotics are kalman filter, complementary filter, low-pass filter, band-pass filter and high-pass filter. Although named differently, all these filters share a common foundation. Here, we will derive a generic filter.
Shimraz/Object-Localization-with-Tensorflow---Coursera
In this course, our primary learning objective is to create and train a multi output convolutional neural network to perform object localization. We will also learn to create custom callbacks and custom metrics in Keras.
Shimraz/ROS_Catkin_WS
DIY ROS Projects
Shimraz/OpenFace
OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.
Shimraz/Pick-and-Place-Manipulator-Robot
In this project, you will remotely access the manipulator in Figure 1 and program it in MATLAB to achieve a pick-and-place sequence of motions. The entire arm is driven by three motors (See Figure 3): • Motor A • Motor B • Motor C In addition to the three actuators, the system has five sensors: • Touch sensor #1 (See Figure 2) • Touch sensor #2 (See Figure 2) • Motor A encoder • Motor B encoder • Motor C encoder
Shimraz/Reconstruction-of-Images-using-PATCH-GANs
Shimraz/Shareat
Food Sharing
Shimraz/Shimraz
Config files for my GitHub profile.
Shimraz/shimraz.github.io