mamcn's repositories
adventures-in-ml-code
This repository holds all the code for the site http://www.adventuresinmachinelearning.com
complex-scheduling-optimization-case-studies
Optimization Case Studies: Generic Time Scheduling Problem (GTSP), Resource-Constrained Project Scheduling Problem (RCPSP) with Pulse Variables
Deep-K-Means-pytorch
Code for ICML 2018 paper 'Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions'
Distributed_DDPG
Parallel implementation of DDPG
DQN-Deep-Q-Network-Atari-Breakout-Tensorflow
Training a vision-based agent with the Deep Q Learning Network (DQN) in Atari's Breakout environment, implementation in Tensorflow.
DQN_vehicle_energy
Code for "Deep Reinforcement Learning-Based Vehicle Energy Efficiency Autonomous Learning System"
EIBalanceLSM
A Liquid State Machine (LSM) with E-I balanced neurons
gradient_control
Gradient control based on relative position to keep two UAVs maintaining a constant distance. The software of UAV is ArduCopter with Dronekit.
IotClustering
Implementation of clustering - hierarchical, K means and DBSCAN
Job-Scheduling-Shortest-job-first-preemptive-python-code
Python code for the scheduling algorithm used in operating systems shortest-remaining-time-first code in python
PyTorch-Tutorial
Build your neural network easy and fast
Reinforcement-learning-with-tensorflow
Simple Reinforcement learning tutorials
RL-Adventure-2
PyTorch0.4 implementation of: actor critic / proximal policy optimization / acer / ddpg / twin dueling ddpg / soft actor critic / generative adversarial imitation learning / hindsight experience replay
scheduling-optimization
Scheduling algorithm solving the job request scheduling problem in the kitchen services industry. This algorithm takes domain specific inputs (set of requests, list of available resources, and prioritized performance objectives) and returns a schedule that maximizes customer utility.
Tensorflow-Tutorial
Tensorflow tutorial from basic to hard
Whale-optimizer-for-Partitoned-HWSN
The problem of network partition in ad-hoc networks received attention in the recent years. Many solutions have been proposed such as algorithms based, heuristics based, approximations based and meta-heuristic based to place additional relay nodes in partitioned heterogeneous wireless sensor networks to resume its operation. However, placing additional relay nodes in the partitioned network is shown an NP-Hard problem, because locations for relay node placements are not known in advance. Meta-heuristics are proven best-suited solutions to solve such kind of NP-Hard problem as well as optimization problem due to their problem independent and stochastic nature. In this research paper, we have introduced a network partition problem and developed a new nature inspired solution called Whale Optimizer to Repair Partitioned Heterogeneous wireless sensor networks (WORPH) based on the social behaviour of whales in the nature. In the proposed solution, a whale tries to find the optimal locations for attacking its prey. We have mimicked the said behaviour of whales in our proposed solution while considering the initial locations of deployed RNs inside disjoint partitions. The observed optimal positions are being used to find the optimal locations for deploying new RNs in such a way that partitioned network is restored in an optimal way. The simulation results are observed and compared with state-of-the-art approaches to prove the effectiveness of our proposed solution.