A naukri.com initiative
ML News
Arxiv
3d
334
Image Credit: Arxiv
Log-Time K-Means Clustering for 1D Data: Novel Approaches with Proof and Implementation
- This thesis introduces optimized algorithms for k-means++ initialization and Lloyd's algorithm, leveraging sorted data, prefix sums, and binary search for improved computational performance.
- The main contributions are: (1) an optimized k-cluster algorithm achieving O(l * k^2 * log n) complexity for greedy k-means++ initialization and O(i * k * log n) for Lloyd's algorithm, and (2) a binary search-based two-cluster algorithm, achieving O(log n) runtime with deterministic convergence to a Lloyd's algorithm local minimum.
- Benchmarks demonstrate over 4500x speedup compared to scikit-learn for large datasets while maintaining clustering quality measured by within-cluster sum of squares (WCSS).
- The algorithms also achieve a 300x speedup in an LLM quantization task, highlighting their utility in emerging applications.
Read Full Article
20 Likes
Arxiv
3d
330
Image Credit: Arxiv
Confidence in the Reasoning of Large Language Models
- There is a growing literature on reasoning by large language models (LLMs), but the discussion on the uncertainty in their responses is still lacking.
- An assessment was conducted to measure the extent of confidence that LLMs have in their answers and how it correlates with accuracy.
- Performance of three LLMs – GPT4o, GPT4-turbo, and Mistral – was evaluated on benchmark sets of questions related to causal judgement, formal fallacies, probability, and statistical puzzles.
- LLMs show better performance than random guessing, but there is variability in their tendency to change initial answers, and they tend to overstate the self-reported confidence score.
Read Full Article
19 Likes
Arxiv
3d
3
Image Credit: Arxiv
MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification
- MIETT (Multi-Instance Encrypted Traffic Transformer) is a model for classifying encrypted network traffic.
- It adopts a multi-instance approach, treating each packet as a distinct instance within a larger bag representing the entire flow.
- MIETT utilizes Two-Level Attention (TLA) layers to capture both token-level and packet-level relationships effectively.
- The model incorporates novel pre-training tasks, PRPP and FCL, to enhance its understanding of temporal and flow-specific dynamics.
Read Full Article
Like
Arxiv
3d
171
Image Credit: Arxiv
Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
- Researchers propose a multimodal joint training framework called MMAudio for high-quality video-to-audio synthesis.
- MMAudio is trained using both video and text-audio data to generate semantically aligned audio samples.
- A conditional synchronization module improves audio-visual synchrony at the frame level.
- MMAudio achieves state-of-the-art performance in audio quality, semantic alignment, and audio-visual synchronization with low inference time and parameter count.
Read Full Article
10 Likes
Arxiv
3d
302
Image Credit: Arxiv
Exploring Machine Learning Engineering for Object Detection and Tracking by Unmanned Aerial Vehicle (UAV)
- Advancements in deep learning methods have led to the inclusion of advanced machine learning algorithms in autonomous systems.
- This research focuses on developing a machine learning pipeline for object detection and tracking by creating a new dataset and refining it for accuracy.
- The dataset was trained on YOLOv4 and Mask R-CNN models, achieving an average loss of 0.1942 and 96% accuracy.
- Experimental results demonstrate the effectiveness of the models in accurately detecting and tracking objects, specifically a Roomba vacuum cleaner.
Read Full Article
18 Likes
Arxiv
3d
203
Image Credit: Arxiv
Investigating Relational State Abstraction in Collaborative MARL
- This paper investigates the impact of relational state abstraction on sample efficiency and performance in collaborative Multi-Agent Reinforcement Learning (MARL).
- The proposed abstraction is based on spatial relationships, leveraging spatial reasoning in real-world multi-agent scenarios.
- The authors introduce MARC (Multi-Agent Relational Critic), a critic architecture that incorporates spatial relational inductive biases by transforming the state into a spatial graph and processing it through a relational graph neural network.
- Empirical analysis shows that MARC outperforms state-of-the-art MARL baselines in terms of sample efficiency, asymptotic performance, and potential for generalization, without requiring complex designs or task-specific engineering.
Read Full Article
12 Likes
Arxiv
3d
163
Image Credit: Arxiv
Cosmology with Persistent Homology: Parameter Inference via Machine Learning
- This article investigates the potential of persistent homology for constraining cosmological parameters and primordial non-Gaussianity amplitudes.
- Persistent homology using persistence images (PIs) performs better than the combined Power Spectrum and Bispectrum (PS/BS) for inferring parameters.
- PIs show promise in constraining primordial non-Gaussianity, particularly for the parameter fNL^loc.
- The combination of PIs with PS/BS provides only marginal gains, indicating little extra information in PS/BS compared to PIs.
Read Full Article
9 Likes
Arxiv
3d
83
Image Credit: Arxiv
Energy consumption of code small language models serving with runtime engines and execution providers
- The study focused on analyzing the impact of deep learning runtime engines and execution providers on energy consumption, execution time, and computing-resource utilization in the context of code Small Language Models (SLMs).
- CUDA execution provider configurations outperformed CPU execution provider configurations in terms of energy consumption and execution time.
- TORCH paired with CUDA demonstrated the greatest energy efficiency, achieving energy savings from 37.99% up to 89.16% compared to other serving configurations.
- Optimized runtime engines like ONNX with the CPU execution provider achieved from 8.98% up to 72.04% energy savings within CPU-based configurations.
Read Full Article
5 Likes
Arxiv
3d
342
Image Credit: Arxiv
Learning charges and long-range interactions from energies and forces
- Accurate modeling of long-range forces is crucial in atomistic simulations for understanding material properties.
- Standard machine learning interatomic potentials often rely on short-range approximations, limiting their applicability in systems with significant electrostatics and dispersion forces.
- The Latent Ewald Summation (LES) method was introduced to capture long-range electrostatics without explicitly learning atomic charges or charge equilibration.
- LES has been successfully applied in benchmarking various challenging systems, showing its effectiveness in inferring physical partial charges, dipole and quadrupole moments, and achieving higher accuracy compared to methods that explicitly learn charges.
Read Full Article
20 Likes
Arxiv
3d
231
Image Credit: Arxiv
TalkWithMachines: Enhancing Human-Robot Interaction for Interpretable Industrial Robotics Through Large/Vision Language Models
- TalkWithMachines aims to enhance human-robot interaction in interpretable industrial robotics.
- The paper explores the integration of Large Language Models (LLMs) and Vision Language Models (VLMs) with robotic perception and control.
- This enables robots to understand and execute commands in natural language and perceive their environment through visual and descriptive inputs.
- The research focuses on four LLM-assisted simulated robotic control workflows, including low-level control, language-based feedback, visual information usage, and task planning.
Read Full Article
13 Likes
Arxiv
3d
103
Image Credit: Arxiv
Predicting Long-Term Student Outcomes from Short-Term EdTech Log Data
- Educational stakeholders are interested in sparse, delayed student outcomes like end-of-year statewide exams.
- Prior work has focused on using long-term usage data to predict outcomes, but this study investigates using short-term log data to predict students' end-of-school year assessments.
- The study utilizes datasets from students in Uganda using a literacy game product and students in the US using two mathematics tutoring systems.
- Findings suggest that 2-5 hours of log usage data can provide valuable insight into students' long-term performance.
Read Full Article
6 Likes
Arxiv
3d
258
Image Credit: Arxiv
DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game
- Researchers propose DualGFL, a novel Federated Learning framework with a Dual-level Game in cooperative-competitive environments.
- DualGFL includes a lower-level hedonic game where clients form coalitions and an upper-level multi-attribute auction game where coalitions bid for training participation.
- At the lower-level, DualGFL introduces a new auction-aware utility function and a Pareto-optimal partitioning algorithm to find a Pareto-optimal partition based on clients' preference profiles.
- At the upper-level, DualGFL formulates a multi-attribute auction game with resource constraints and derives equilibrium bids to maximize coalitions' winning probabilities and profits.
Read Full Article
15 Likes
Arxiv
3d
342
Image Credit: Arxiv
The Impact of Cut Layer Selection in Split Federated Learning
- Split Federated Learning (SFL) combines federated learning and split learning.
- SFL partitions a neural network at a cut layer, with initial layers on clients and remaining layers on a training server.
- SFL-V1 maintains separate server-side models for each client, while SFL-V2 maintains a single shared model for all clients.
- Cut layer selection significantly affects the performance of SFL-V2, outperforming FedAvg on certain datasets.
Read Full Article
20 Likes
Arxiv
3d
215
Image Credit: Arxiv
NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning
- Researchers have introduced the Nutritional Graph Question Answering (NGQA) benchmark
- NGQA is the first graph question answering dataset designed for personalized nutritional health reasoning
- The benchmark leverages data from the National Health and Nutrition Examination Survey (NHANES) and the Food and Nutrient Database for Dietary Studies (FNDDS)
- NGQA effectively challenges existing models and advances GraphQA research with a novel domain-specific benchmark
Read Full Article
12 Likes
Arxiv
3d
394
Image Credit: Arxiv
Predicting Artificial Neural Network Representations to Learn Recognition Model for Music Identification from Brain Recordings
- Recent studies have shown that artificial neural network (ANN) representations can resemble cortical representations when exposed to the same auditory inputs.
- This study proposes a new approach by using ANN representations as a supervisory signal to train recognition models for music identification using non-invasive brain recordings.
- By training an EEG recognition model to predict ANN representations associated with music identification, significant improvement in classification accuracy is observed.
- This research has potential implications for advancing brain-computer interfaces, neural decoding techniques, and our understanding of music cognition.
Read Full Article
23 Likes
For uninterrupted reading, download the app