Published inAI AdvancesMathematical Foundation Underpinning Reinforcement LearningThe ability to learn from experience is a deeply fundamental process, one that is subject to significant research in neuroscience; after…Dec 31, 20248Dec 31, 20248
Published inAI AdvancesReinforcement Learning: Teaching an Agent to Operate a Power PlantAn introduction to the mathematical concepts of reinforcement learning and a practical guide to implementationNov 14, 20244Nov 14, 20244
Published inAI AdvancesGenerative AI: Transformers For Molecular DesignBuilding a transformer model for generating molecules with desired physical properties. A pytorch implementationAug 20, 2024Aug 20, 2024
Published inTowards AIBuilding a Multi-Agent System to Accomplish Complex TasksA simple framework for multi-agent systems allowing specialized agents to communicate and collaborate for multi-step tasks.May 24, 2024May 24, 2024
Published inTowards AIGraphs in Motion: Spatio-Temporal Dynamics with Graph Neural NetworksThe concept behind ST-GNNs and a Pytorch Implementation for time series forecastingApr 8, 20241Apr 8, 20241
Published inTDS ArchiveStructure and Relationships: Graph Neural Networks and a Pytorch ImplementationUnderstanding the mathematical background of graph neural networks and implementation for a regression problem in pytorchMar 5, 20243Mar 5, 20243
Published inTDS ArchiveBuilding Blocks of Time: The Mathematical Foundation and Python Implementation of RNNsIs being able to build and train machine learning models from popular libraries sufficient for machine learning users? Probably not for too…Jan 20, 20244Jan 20, 20244
Published inTDS ArchiveGenerative AI: Synthetic Data Generation with GANs using PytorchDemystifying Complexity: Beyond Images and Language ModelsJan 15, 20242Jan 15, 20242
