AI-For-Beginners — 12 Weeks, 24 Lessons, AI for All!
AIの入門コースを提供する。
AI入門
MLINFO COLLECTION
深層学習
記事一覧
19 / 45leedl-tutorial — 《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
deep-learning
MOSHO: A Native Discrete Shark-Inspired Metaheuristic for Hardware-Aware Neural Architecture Search
Hardware-aware neural architecture search (NAS) requires jointly optimizing predictive accuracy and device-specific latency over discrete search spaces. While multi-objective swarm optimizers show…
deep-learning
When Are Nesterov Trajectories Eventually Locally Minimizing?
We revisit the variational characterization of Nesterov's celebrated method and study when Nesterov trajectories are eventually locally minimizing in a variational sense, a notion that we define…
deep-learning
Joint Service Depth and Priority Design in Queueing Systems
In AI-assisted service systems, the server can choose how much processing effort to spend on each job, which we call the service depth. Deeper reasoning improves output quality but occupies the…
deep-learning
The kernel mean embedding of a random probability distribution and its principal components
Given a random probability distribution \(F\), whose realizations are defined on \(\mathbb R^d\), and a kernel \(k\), our aim is to analyze the properties of the kernel mean embedding, \(μ_F\), of…
deep-learning
Not All Mislabels Are Equal: Efficient Task-Aware Auditing with Confidence Sequences
We study efficient, adaptive auditing of categorical labels in a fixed dataset, motivated by biodiversity-credit programs in which expert verification of species records is costly and downstream…
deep-learning
Kernelised covariance matrices, dimension reduction and imbalanced spectral clustering
The Gaussian Mixture Model (abbrv. GMM) is a classic generative model for clustered data, for which spectral clustering based on dimension reduction via PCA has been an effective framework.
deep-learning
Singular Geometry of Low-Rank Adaptation
Low-rank adaptation (LoRA) is now a standard approach to parameter-efficient fine-tuning of large neural networks. Its low-rank factorization is inherently non-identifiable, making LoRA a singular…
deep-learning
Neural LoFi with Backward Coupling: A Spectral Theory of Cross-Layer Feature Learning
During joint training, backpropagation allows later layers to reshape earlier representations, a feedback mechanism absent from purely layer-wise learning. We extend Neural Low-Degree Filtering…
deep-learning
Structure and Exact Certification of Nonnegative Tensor Decompositions
We study the structure and exact certification of nonnegative tensor decompositions supplied through rational factor matrices. Every failure of minimality or essential uniqueness contains an…
deep-learning
Sparse Bayesian Neural Networks via Sticky Piecewise Deterministic Markov Processes
There is growing evidence that the performance of a neural network depends largely on a small subset of its weights, which are typically identified by training a dense network and pruning it…
deep-learning
Strongly Adaptive Online Learning with Time-Varying Movement Costs
We study strongly adaptive regret for Online Convex Optimization (OCO) with time-varying movement costs, a setting that evaluates a learner's performance over arbitrary sub-intervals. This framework…
deep-learning
Score-Preserving Continual Lasso under Task Shift
Continual learning (CL) aims to learn from sequential tasks while mitigating catastrophic forgetting when historical data are no longer accessible. We study continual learning for high-dimensional…
deep-learning
Exact Global Minimax Risk near Nonidentification
We study squared-error estimation when a nuisance parameter is unidentified on a submodel but affects a target that vanishes there. For models with higher-order profile expansions, we give sufficient…
deep-learning
PAFS: Perturbation-Aware Firing Scaffolds for Robust Event-Based SNNs
Event-based spiking neural networks (SNNs) encode information through temporal firing dynamics, but the same stateful computation makes their predictions sensitive to event loss, timestamp jitter,…
deep-learning
Empirical concentration for chains with infinite memory
Concentration inequalities for time series usually involve unknown quantities measuring dependence. This prevents their direct use as confidence bounds, or as criteria for learning algorithms.
deep-learning
Covariance-Informed Ensemble Score Filtering: Embedding Localized Covariance Geometry into Score-Based Transport
Background-error covariance models are central to atmospheric data assimilation because they spread partial observational information across space, variables, and dynamically coupled scales. Ensemble…
deep-learning
DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting
Non-stationarity induces test-time distribution shifts in time series forecasting (TSF), resulting in forecast residuals between predictions and the corresponding ground truth. Recent works on…
deep-learning
A Resource-Efficient and Precision-Scalable FPGA Accelerator for Spiking Neural Networks Using Minifloat Arithmetic
Spiking neural networks (SNNs) are well suited to event-driven edge intelligence, but the arithmetic complexity, memory footprint, and power consumption associated with conventional floating-point…
deep-learning
Every Weight Is a Path of Shared Discrete Decisions
We introduce TWIG (Tree-structured Weights with Inherited Gates), a representation in which every weight of a neural network is the end of a path of small discrete decisions: a sign, a shift by a…
deep-learning
Sub-monolayer tracking of molecular states at buried interfaces
Phenomena responsible for emerging technologies originate from novel molecular states at buried interfaces. Yet quantitatively resolving these features is out of reach in most cases.
deep-learning
Nested Sparsity for Scalable Pretraining and Continual Learning
Mixture-of-experts (MoE) transformers, the standard backbone for modern large-scale deep learning, employ conditional computation: only a sparse subset of model weights is used in each forward pass.…
deep-learning
Does LeWorldModel Preserve Local Action Geometry?
We examine how closely pretrained LeWorldModel (LeWM) reproduces the effects of small action changes. Using matched simulator and model responses, we measure action sensitivity with Gram matrices at…
deep-learning