Cristian LeoinTowards Data ScienceKeep the Gradients FlowingOptimizing Sparse Neural Networks: Understanding Gradient Flow for Faster Training, and Better Performance in Deep Learning Models.4d ago34d ago3
Cristian LeoinInsiderFinance WireMonte-Carlo Simulation for Portfolio OptimizationBuilding a Python App for portfolio optimization using Monte Carlo Simulation.Sep 242Sep 242
Cristian LeoThe Math Behind TabTransformerThe king of tabular data: TabTransformer. Here’s how the transformer architecture wins over classical Machine LearningSep 101Sep 101
Cristian LeoThe Math Behind Vision TransformersDeep Dive into the Vision Transformer Architecture, the forefront of Computer Vision. Let’s explore its math, and build it with PyTorch.Sep 43Sep 43
Cristian LeoThe Math Behind Gated Adaptive Network for Deep Automated Learning of FeaturesThe Deep Learning model that finally beats XGBoost on tabular data. Let’s delve into its math, code, advantages and limitations.Aug 13Aug 13
Cristian LeoData Science Roadmap: The Hard OneThe 2024 Data Science Roadmap to learn every model from scratch, from Linear Regression to Transformers.Aug 6Aug 6
Cristian LeoThe Math Behind TransformersDeep Dive into the Transformer Architecture, the key element of LLMs. Let’s explore its math, and build it from scratch in Python.Jul 255Jul 255
Cristian LeoinTowards Data ScienceThe Math Behind Multi-Head Attention in TransformersDeep Dive into Multi-Head Attention, the secret element in Transformers and LLMs. Let’s explore its math, and build it from scratch.Jul 163Jul 163
Cristian LeoinTowards Data ScienceAutoML with AutoGluon: Transform Your ML Workflow with Just Four Lines of CodeHow AutoGluon Dominated Kaggle Competitions and How You Can Beat It. The algorithm that beats 99% of Data Scientists with 4 lines of code.Jul 33Jul 33
Cristian LeoinTowards Data ScienceMachine Learning Optimization with OptunaHow to fine-tune every machine learning algorithm in Python: The ultimate guide to machine learning optimization with OptunaJun 252Jun 252