fastbook — The fastai book, published as Jupyter Notebooks
The fastai book, published as Jupyter Notebooks
deep-learning
MLINFO COLLECTION
深層学習
記事一覧
41 / 45DiffusionOPSD — 🔥 On-Policy Self-Distillation in Diffusion Models
🔥 On-Policy Self-Distillation in Diffusion Models
deep-learning
FidLIF: Parallel Training of High-Fidelity Spiking Neurons with Exact BPTT
Although spiking neural networks (SNNs) show promise in energy-efficient computing through event-driven computation and stateful temporal processing, their recurrent membrane dynamics render their…
deep-learning
Time Window Optimization for Motor Imagery Classification via Temporal Structure Embedded Reinforcement Learning
Online motor imagery-based brain-computer interfaces (MI-BCIs) typically decode continuous EEG using fixed-length sliding windows that may be misaligned with neural events. Existing window…
deep-learning
The Complexity of Exact and Approximate Nash Equilibria in Anonymous Games
We prove that, for every fixed rational $c>0$, computing a $2^{-n^c}$-approximate Nash equilibrium in an $n$-player two-strategy anonymous game is $\mathsf{PPAD}$-complete. This holds even when one…
deep-learning
DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning
Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candidates. The key difficulty is that neural…
deep-learning
Digital-Twin-Referenced Belief-Guided Q-Learning for Jammer Identification and Beam-Power Control in a mmWave Model
Next-generation wireless networks are expected to support high data rates and reliable connectivity while meeting requirements for energy efficiency, resource management, and communication security.…
deep-learning
naspaclust: A hybridisation of spatial fuzzy clustering with nature-inspired optimisation
We present an overview of R package called \texttt{naspaclust}, a tool for spatial fuzzy clustering improvement by hybridising the Fuzzy Geographically Weighted Clustering (FGWC) with nature-inspired…
deep-learning
Thompson Sampling for Learning in Zero-Sum Games
Thompson sampling (TS) achieves logarithmic and asymptotically optimal regret in classical stochastic bandits, but its behavior in multi-agent learning remains less understood. We study TS in an…
deep-learning
Matched Specialization, Different Adaptation: Second-Moment Structure in Shared Representations
Small Adam-trained shared-representation networks can reach equivalent selected mean readout measurements yet respond differently to the same further learning. We use state interventions to separate…
deep-learning
Fair Allocation with Dichotomous Preferences over Item Complements
We study the problem of fair allocation when agents have dichotomous submodular preferences over groups of, rather than individual, items. These preferences naturally extend existing models, and have…
deep-learning
Representation Theorems for Actual Powers over Two-Agent General Concurrent Game Frames
One of the most well-known connections between logic and games is Pauly's representation theorem: the induced powers of individuals and coalitions in concurrent game frames correspond, in a precise…
deep-learning
CoFlu-Brain: An fMRI Connectivity Foundation Model with Cofluctuation-Based Pretraining
Functional magnetic resonance imaging (fMRI) commonly characterizes large-scale brain organization through functional connectivity (FC). However, an observed FC matrix is not a fixed brain graph but…
deep-learning
FENAS: A Few-Shot Meta-Ensembling Framework for Efficient Neural Architecture Search with Synergized Zero-Cost Proxies
Efficient neural architecture search (NAS) requires accurate performance estimation under limited evaluation budgets. Existing zero-cost proxies (ZCPs) provide fast training-free signals, but each…
deep-learning
Compute-Optimal Scaling Laws for Spiking Language Models
Spiking neural networks target energy-efficient language modeling through sparse, binary activations, but the efficiency-accuracy tradeoff of spiking language models is uncharacterized at scale. We…
deep-learning
RELAGRAM: Recursive Latent Graph Model for the Capacitated Vehicle Routing Problem
Latent recursion repeatedly processes internal representations through the same neural network. Recent work has shown this approach to be effective on structured reasoning tasks such as Sudoku and…
deep-learning
What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories
Publishers and funders increasingly ask authors to disclose how AI tools contributed to a piece of research. In computational work the repository is where an author or an auditor would look for the…
deep-learning
Do Artificial Neural Networks Need Dendritic Nanotubes? Two Reasons for Shrinking Importance Estimates in Continual Learning
Regularization-based continual learning protects each parameter in proportion to an estimate of its importance, yet these estimates come from finite samples and heuristics and are used as if they…
deep-learning
Algorithms with Smoothed Polynomial-Time Complexity for Deterministic Discounted-sum and Mean-payoff Games
Turn-based deterministic games on graphs are two-player zero-sum games played on finite directed graphs, where the vertex set is partitioned between the Max and the adversarial Min Player. The…
deep-learning
DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness
Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplified by sleep state misperception in paradoxical…
deep-learning
The value of information and the emergence of communication in evolved e-puck robots
We study when communication emerges between autonomous agents and what role an innate action selection architecture plays. Two e-puck robots, reconstructed in PyBullet from their Webots model and…
deep-learning
HunyuanVideo — HunyuanVideo: A Systematic Framework For Large Video Generation Model
画面の生成モデルであるHunyuanVideoを開発した。HunyuanVideoは、複雑なシーケンスを生成する能力を持つ。
画面の生成モデルへの応用
miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning
Native NVFP4 promises to accelerate reinforcement learning (RL) for large language models (LLMs), but achieving stable learning across separate training and sampling engines remains challenging. We…
deep-learning
Risk-minimizing GUE-implementations of truthful reporting in a Dynamic Social Choice Problem
The Guaranteed Utility Mechanism (GUM) was introduced to implement efficiency in Guaranteed Utility Equilibrium (GUE) in dynamic social choice problems. We show that this mechanism also has a…
deep-learning