23171
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
Here are some Hyperparameter (HP) tuning & optimization packages you can use in your projects:
- Scikit-Optimize: https://lnkd.in/gbJqdFq9
- Optuna: https://optuna.org/
- Hyperopt: https://lnkd.in/gPSRhW_6
- Ray.tune: https://lnkd.in/gzrDAbHg
- Keras tuner: https://lnkd.in/g_HDHiug
- BayesianOptimization: https://lnkd.in/g8UKEvjc
- Metric Optimization Engine (MOE): https://lnkd.in/g89JGFB2
- Spearmint: https://lnkd.in/gJwG3AwE
- GPyOpt: https://lnkd.in/g4cWEBPz
- SigOpt: https://sigopt.com/
✅@Machine_learn
Recommendation with Generative Models
📓 Book
✅@Machine_learn
📑 Advancing biomedical discovery and innovation in the era of big data and artificial intelligence
💥 Perspective Article
📎 Study the paper
✅@Machine_learn
Exercises in Machine Learning
📚 Book
✅@Machine_learn
OmniGen: Unified Image Generation
Paper: https://arxiv.org/pdf/2409.11340v1.pdf
Code: https://github.com/vectorspacelab/omnigen
Dataset: DreamBooth | MagicBrush
✅@Machine_learn
Financial Machine Learning
📓 book
✅@Machine_learn
📃Large Language Models on Graphs: A Comprehensive Survey
📎 Study paper
✅@Machine_learn
با عرض سلام دو پکیچ یادگیری ماشین و یادگیری عمیق را برای دوستانی که می خواهند تا فرداشب با تخفیف ۵۰٪ مجدد قرار دادیم این تخفیف اخرین سری از تخفیف های این دو پکیچ می باشد
1: introduction to machine learning
2: Regression (linear and non-linear)
3: Tensorflow introduction
4: Tensorflow computaion graph
5: Tensorflow optimizer and loss function
6: Tensorflow linear and non linear regression
7: logistic regression
8: Tensorflow regression
___________
9: introduction to traditional machine learning
*10: knn and desicion tree
*11: desicion tree and Naive bayes
*12: desicion tree, knn, Naive bayes implementation
*13: k-means
*14: Guassion Mixture Model(GMM)
*15: implementation K-means and GMM
_
16: introduction to Artificial Neural Network
17: Multi-level Neural Network
18: Introduction to Convolution Neural Network
19: Tensorflow Multi-level Neural Network
20:Tensorflow CNN
21:CNN image clasaification
22: Cnn text clasaification
23: Recurrent Neural Network(RNN)
جهت تهیه می تونین به ایدی بنده مراجعه کنین
@Raminmousa
Python for OSINT. 21-day course for beginners
📚 Book
✅@Machine_learn
LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Paper: https://arxiv.org/pdf/2409.06666v1.pdf
Code: https://github.com/ictnlp/llama-omni
✅@Machine_learn
Algorithm Design and Analysis
📓 Book
✅@Machine_learn
فقط نفر ٤ ام باقي مونده.
@Raminmousa
⚡️ Most of the models from Mistral are now available for free via the API
What is this attraction of unprecedented generosity? Your queries will probably be used to train new models (although this is not accurate).
https://docs.mistral.ai/getting-started/models/
@Machine_learn
با عرض سلام
مقاله ی زیر تماما نگارش شده و اماده سابمیت از دوستان کسی خواست نفرات ۳ و ۴ اش خالی هست.
IEEE Geoscience and Remote Sensing Letter
Impact factor 4
CiteScore 7.6
------------------------------
Title: Enhanced-HisSegNet: An Enhanced Histagram Layered Segmentation Network for SAR Image-based Flood Segmentation
------------------------------
Abstract:
Floods are among the most frequent natural disasters, causing loss of life and significant economic and environmental damage, with direct impacts on agriculture, urban infrastructure, and transportation networks. Therefore, it is crucial to accurately and efficiently identify flooded areas in the aftermath of such events. Synthetic Aperture Radar (SAR) imagery plays a vital role in this process, as water surfaces reflect less microwave energy compared to land due to their smooth texture and low surface roughness. In this study, we present a multimodal fusion strategy that enhances the existing model by Turkmenli et al. [1] through the integration of fine-tuned histograms and Deep Neural Networks (DNNs) for improved flood mapping. Specifically, we introduce fine-tuned histogram extraction layers designed for SAR data, which are integrated into Deep Segmentation Neural Networks (DSNNs). The model was tested on two real SAR datasets, with cross-dataset validation using an external cohort, representing a second innovation in our approach. Experimental results demonstrate that our model, with fine-tuned histogram layers, outperforms previous approaches by up to 4% in intersection over union (IoU) and provides a comprehensive evaluation through metrics such as Precision, Recall, Average Precision (AP), Mean Average Precision (mAP), False Positive Rate (FPR), and Mean Average Recall (mAR). Importantly, these improvements come with minimal additional learnable parameters. The code for this work will be made available at https://github.com/Mohsena1990/Enhanced-HistSegNet
@Raminmousa
@Machine_learn
@Paper4monry
Paper: Understanding LLMs: A Comprehensive Overview from Training to Inference
Tags: LLMs
✅@Machine_learn
📃 Natural Language Processing Methods for the Study of Protein-Ligand Interactions
🗓Publish year: 2024
📎 Study the paper
✅@Machine_learn
Improving LLM Reasoning using SElf-generated data:RL and Verifiers
📓 Slides
✅@Machine_learn
اسامی ۲، ۳ و ۵ این پیپر واگذار میشه:
Title: Computation-Efficient Neural Network Based on
Model’s Saliency Performance
Abstract
The increasing complexity of deep neural networks has resulted in significant computational overhead, limiting their deployment in real-time and resource-constrained environments. While model pruning and quantization have been explored extensively, they often do not consider the model's saliency performance, which reflects how critical specific neurons or layers are to the overall task. This paper presents a Computation-Efficient Neural Network framework that uses model saliency to identify and preserve the most critical components of the network while reducing the computational cost by pruning less significant elements. The approach computes the saliency score of each layer or neuron, evaluates its contribution to the model's performance, and prunes the less salient parts without significant accuracy loss. By focusing on saliency, this method maintains robust performance while reducing both memory and computational demands. Experiments on image classification tasks demonstrate the effectiveness of this saliency-based pruning in achieving high efficiency with minimal performance degradation.
Keyword: Deep Learning Model Compression,
Convolutional Neural Networks
Medical Image Classification,
Quantization-Aware Training,
Computational Efficiency
* Submission: Nature Springer
** This paper is written by two PhD students from top universities in the USA.
*** A one-page summary is attached.
@reza_alvandi
با عرض سلام ٨٠٪ نگارش مقاله زير انجام شده است
title: A survey of generative adversarial network on next generation networks:5G and 6G Networks
مقاله در ابتدا در اركايو ثبت ميشه و كامل شدش براي ژورنال مربوطه فرستاده ميشه.
دوستاني كه نياز دارن ميتونن در اين مقاله شركت كنند. اين مقاله فقط با سه نفر سابميت ميشه كه نفر اول خودم هستم و جايگاه دو و سوم خالي داره.
@Raminmousa
@Paper4money
@Machine_learn
📃SOCIAL NETWORK ANALYSIS: FROM GRAPH THEORY TO APPLICATIONS
📎 Study paper
✅@Machine_learn
INDCAPS: The IndRNN Capsule Approach for Persian Multi-
Domain Sentiment Analysis
یکی از بحث های که این روزها خیلی ترند هستش بحث مربوط به طبقه بندی احساسات چندجمله ای می باشد. در این مقاله ما یک مجموعه داده که روی داده های دیجی کالا می باشند رو جمع اوری کردیم. جمع اوری این داده ها ۳ ماه طول کشیده و این ریپورت گزارش مربوط به این داده هاست.
@Raminmousa
@Machine_learn
MiniCPM-V
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Creator: OpenBMB
Stars ⭐️: 11.4k
Forked By: 798
GitHub Repo:
https://github.com/OpenBMB/MiniCPM-V
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join ✅/channel/deep_learning_proj
✅@Machine_learn
Fundamentals of Data Engineering
📌 Book
📌Download
✅@Machine_learn
با عرض سلام
مقاله ی زیر تماما نگارش شده و اماده سابمیت از دوستان کسی خواست نفر ۴ اش خالی هست.
IEEE Geoscience and Remote Sensing Letter
Impact factor 4
CiteScore 7.6
------------------------------
Title: Enhanced-HisSegNet: An Enhanced Histagram Layered Segmentation Network for SAR Image-based Flood Segmentation
------------------------------
Abstract:
Floods are among the most frequent natural disasters, causing loss of life and significant economic and environmental damage, with direct impacts on agriculture, urban infrastructure, and transportation networks. Therefore, it is crucial to accurately and efficiently identify flooded areas in the aftermath of such events. Synthetic Aperture Radar (SAR) imagery plays a vital role in this process, as water surfaces reflect less microwave energy compared to land due to their smooth texture and low surface roughness. In this study, we present a multimodal fusion strategy that enhances the existing model by Turkmenli et al. [1] through the integration of fine-tuned histograms and Deep Neural Networks (DNNs) for improved flood mapping. Specifically, we introduce fine-tuned histogram extraction layers designed for SAR data, which are integrated into Deep Segmentation Neural Networks (DSNNs). The model was tested on two real SAR datasets, with cross-dataset validation using an external cohort, representing a second innovation in our approach. Experimental results demonstrate that our model, with fine-tuned histogram layers, outperforms previous approaches by up to 4% in intersection over union (IoU) and provides a comprehensive evaluation through metrics such as Precision, Recall, Average Precision (AP), Mean Average Precision (mAP), False Positive Rate (FPR), and Mean Average Recall (mAR). Importantly, these improvements come with minimal additional learnable parameters. The code for this work will be made available at https://github.com/Mohsena1990/Enhanced-HistSegNet
@Raminmousa
@Machine_learn
@Paper4monry
🌟 GRIN MoE: Mixture-of-Experts от Microsoft.
🟢total parameters: 16x3.8B;
🟢active parameters: 6.6B;
🟢context length: 4096;
🟢number of embeddings 4096;
🟢number of layers: 32;
✅/channel/deep_learning_proj
🟡Arxiv
🟡Demo
🖥Github
@Machine_learn
⭐️ ثبتنام استارکمپ Machine Learning پیشرفته دانشکار شروع شد!
💻📊 مناسب افراد فعال در حوزه دیتا ساینس و دیتا آنالیز و که به دنبال ارتقا خود در این زمینه هستن.
🔽 مباحث این استارکمپ:
🔸Ensemble Algorithm
🔸Anomaly Detection
🔸Machine Learning Pipeline
🔸Feature Selection
💼 این دوره پروژهمحوره با نیازهای شرکتها تطابق داره تا شما رو برای بازار کار و ارتقا شغلی آماده کنه.
🤖🐍 برای این دوره باید آشنایی مقدماتی با پایتون و ماشین لرنینگ داشته باشین.
✅ ثبتنام و مشاوره رایگان:
🔗 https://dnkr.ir/2Mze4
Mathematical theory of deep learning
📚 Book
✅@Machine_learn
فقط نفر ٤ ام باقي مونده.
Читать полностью…
با عرض سلام دوستان اين گروه ها كامل پرشده بجز بخش طبقه بندي پزشكي كه نفر پنجم يه گروه جا هست .
@Raminmousa
Title: DEEP LEARNING INTERVIEWS
Author: SHLOMO KASHANI
Tags: Deep_learning
✅@Machine_learn