Beyond Simple Inversion: Building and Applying Inverse Neural Networks
Author(s): Shenggang Li Originally published on Towards AI. Theory, training tricks, and real‑world case studies — solving multi‑root equations and beyondPhoto by Marisa Harris on Unsplash Inverse problems ask a fundamental question: Given the output y, what was the input x? Traditional …
Reinforcement Learning-Enhanced Gradient Boosting Machines
Author(s): Shenggang Li Originally published on Towards AI. A Novel Approach to Integrating Reinforcement Learning within Gradient Boosting Internal Optimization for Superior Predictive PerformancePhoto by Austin Neill on Unsplash In this post, I demonstrate how reinforcement learning (RL) can directly enhance the …
Adaptive Multi-Teacher Distillation for Enhanced Supervised Learning
Author(s): Shenggang Li Originally published on Towards AI. A Novel Approach for Dynamically Combining Multiple Predictive Models into a Lightweight High-Performance Student ModelPhoto by Damon Hall on Unsplash In practical supervised learning, using a single predictive model like XGBoost, LightGBM, or Random …
Reimagining Diffusion Models: Autoregressive Priors for Efficient Initialization
Author(s): Shenggang Li Originally published on Towards AI. Exploring a Novel Approach to Diffusion Initialization with Intuitive Illustrations, Applications This member-only story is on us. Upgrade to access all of Medium. Photo by Gary Fultz on Unsplash Diffusion models have become a …
Practical Guide to Distilling Large Models into Small Models: A Novel Approach with Extended Distillation
Author(s): Shenggang Li Originally published on Towards AI. Comparing Traditional and Enhanced Step-by-Step Distillation: Adaptive Learning, Cosine Similarity, and Curriculum-Based Rationale Supervision This member-only story is on us. Upgrade to access all of Medium. Photo by Thorium on Unsplash In this paper, …
Exploring LoRA as a Dynamic Neural Network Layer for Efficient LLM Adaptation
Author(s): Shenggang Li Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. Photo by Jakub Żerdzicki on Unsplash LLMs need constant updates — legal AI must learn new laws, finance chatbots need fresh market …
Building AI-Powered Chatbots with Gemini, LangChain, and RAG on Google Vertex AI
Author(s): Shenggang Li Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. A Step-by-Step Guide to Configuring Google Vertex AI, Leveraging the Gemini API, and Integrating Knowledge Bases for Intelligent Conversational Applications Photo by …
Investigating Transformer Attention and Reinforcement Learning Dynamics Using Self‑Generated Structural Data
Author(s): Shenggang Li Originally published on Towards AI. Cracking the Code: Synthetic Data as the Key to Understanding and Enhancing LLMs This member-only story is on us. Upgrade to access all of Medium. Photo by Joshua Sortino on Unsplash Building large language …
A Neural Sparse Graphical Model for Variable Selection and Time-Series Network Analysis
Author(s): Shenggang Li Originally published on Towards AI. A Unified Adjacency Learning and Nonlinear Forecasting Framework for High-Dimensional Data This member-only story is on us. Upgrade to access all of Medium. Photo by Susan Q Yin on Unsplash Imagine a spreadsheet with …
Beyond Buy-and-Hold: Dynamic Strategies for Unlocking Long-Term Stock Growth
Author(s): Shenggang Li Originally published on Towards AI. Harnessing Survival Analysis and Markov Decision Processes to Surpass Static ETF Performance This member-only story is on us. Upgrade to access all of Medium. Photo by Chris Liverani on Unsplash Have you ever heard …
DeepSeek-TS+: A Unified Framework for Multi-Product Time Series Forecasting
Author(s): Shenggang Li Originally published on Towards AI. Leveraging State-Space Enhanced Multi-Head Latent Attention and Group Relative Policy Optimization (GRPO) for Adaptive Forecasting This member-only story is on us. Upgrade to access all of Medium. Photo by Solen Feyissa on Unsplash I …
Reinforcement Learning-Driven Adaptive Model Selection and Blending for Supervised Learning
Author(s): Shenggang Li Originally published on Towards AI. Inspired by Deepseeker: Dynamically Choosing and Combining ML Models for Optimal Performance This member-only story is on us. Upgrade to access all of Medium. Photo by Agence Olloweb on Unsplash Machine learning model selection …
Event-Driven Prediction: Expanding Mamba State Space Models for Conditional Forecasting
Author(s): Shenggang Li Originally published on Towards AI. A Novel Approach Combining Markov Decision Theory and Neural State Space Models for Stock Price Prediction This member-only story is on us. Upgrade to access all of Medium. Photo by Ella Jardim on Unsplash …
Unlocking the Potential of Meta LLaMA: A Deep Dive into Its Design, Architecture, and Applications
Author(s): Shenggang Li Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium. Photo by Dima Solomin on Unsplash Let’s explore Meta’s LLaMA, one of the coolest and most powerful language models. If you’ve ever …
Bayesian State-Space Neural Networks (BSSNN): A Novel Framework for Interpretable and Probabilistic Neural Models
Author(s): Shenggang Li Originally published on Towards AI. Integrating Bayesian Theory, State-Space Dynamics, and Neural Network Structures for Enhanced Probabilistic Forecasting This member-only story is on us. Upgrade to access all of Medium. Photo by Planet Volumes on Unsplash When building supervised …
Recent Posts
