23171
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
🔥 nn-zero-to-hero
🖥 Github
@Machine_learn
با عرض سلام پروژه Biopars رو شروع كرديم نفر ٥ ام از اين مقاله رو نياز داريم.
این کار تحت نظر استاد
Rex (Zhitao) Ying
انجام میشه.
link: https://scholar.google.com.au/citations?user=6fqNXooAAAAJ&hl=en
BioPars: a pre-trained biomedical large language model for persian biomedical text mining.
١- مراحل اوليه: جمع اوري متن هاي فارسي بيولوژيكي از منابع (...)
٢- پيش پردازش متن ها و تميز كردن متن ها
٣- اموزش ترنسفورمرها ي مورد نظر
٤- استفاده از بردارها ي اموزش داده شده در سه تسك (...)
هزينه سرور به ازاي هر ساعت ١.٢ دلار مي باشد. و حدود ٢ هزار ساعت براي اموزش مدل زباني نياز ميباشد.
دوستاني كه نياز دارن مي تونن به تيم ما اضافه بشن
🔸🔸🔸🔸🔸
@Raminmousa
📄 RNA Sequencing Data: Hitchhiker's Guide to Expression Analysis
📎 Study the paper
@Machine_learn
CogAgent: A Visual Language Model for GUI Agents
Paper: https://arxiv.org/pdf/2312.08914v3.pdf
CVPR 2024: http://openaccess.thecvf.com//content/CVPR2024/papers/Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper.pdf
Code1: https://github.com/thudm/cogvlm
Code2: https://github.com/digirl-agent/digirl
Code3: https://github.com/THUDM/CogAgent
Dataset: TextVQA
💠@Machine_learn
Python for Everybody Exploring Data Using Python 3
📓 book
@Machine_learn
📚 Transfer Learning for CNNs: Leveraging Pre-trained Models
Transfer learning is a machine learning technique where a pre-trained model is used as a starting point for a new task. In the context of convolutional neural networks (CNNs), this means using a CNN that has been trained on a large dataset for one task (e.g., ImageNet) as a foundation for a new task (e.g., classifying medical images).
🌐 Why Transfer Learning?
1. Reduced Training Time: Training a CNN from scratch on a large dataset can be computationally expensive and time-consuming. Transfer learning allows you to leverage the knowledge learned by the pre-trained model, reducing training time significantly.
2. Improved Performance: Pre-trained models have often been trained on massive datasets, allowing them to learn general-purpose features that can be useful for a wide range of tasks. Using these pre-trained models can improve the performance of your new task.
3. Smaller Datasets: Transfer learning can be particularly useful when you have a small dataset for your new task. By using a pre-trained model, you can augment your limited data with the knowledge learned from the larger dataset.
💸 How Transfer Learning Works:
1. Choose a Pre-trained Model: Select a pre-trained CNN that is suitable for your task. Common choices include VGG16, ResNet, InceptionV3, and EfficientNet.
2. Freeze Layers: Typically, the earlier layers of a CNN learn general-purpose features, while the later layers learn more task-specific features. You can freeze the earlier layers of the pre-trained model to prevent them from being updated during training. This helps to preserve the learned features
3. Add New Layers: Add new layers, such as fully connected layers or convolutional layers, to the end of the pre-trained model. These layers will be trained on your new dataset to learn task-specific features.
4. Fine-tune: Train the new layers on your dataset while keeping the frozen layers fixed. This process is called fine-tuning.
🔊 Common Transfer Learning Scenarios:
1. Feature Extraction: Extract features from the pre-trained model and use them as input to a different model, such as a support vector machine (SVM) or a random forest.
2. Fine-tuning: Fine-tune the pre-trained model on your new dataset to adapt it to your specific task.
3. Hybrid Approach: Combine feature extraction and fine-tuning by extracting features from the pre-trained model and using them as input to a new model, while also fine-tuning some layers of the pre-trained model.
Transfer learning is a powerful technique that can significantly improve the performance and efficiency of CNNs, especially when working with limited datasets or time constraints.
🚀 Common Used Transfer Learning Meathods:
1️⃣. VGG16: A simple yet effective CNN architecture with multiple convolutional layers followed by max-pooling layers. It excels at image classification tasks.
2️⃣ . MobileNet: Designed for mobile and embedded vision applications, MobileNet uses depthwise separable convolutions to reduce the number of parameters and computational cost.
3️⃣ DenseNet: Connects each layer to every other layer, promoting feature reuse and improving information flow. It often achieves high accuracy with fewer parameters.
4️⃣ Inception: Employs a combination of different sized convolutional filters in parallel, capturing features at multiple scales. It's known for its efficient use of computational resources.
5️⃣ ResNet: Introduces residual connections, enabling the network to learn more complex features by allowing information to bypass layers. It addresses the vanishing gradient problem.
6️⃣ EfficientNet: A family of models that systematically scale up network width, depth, and resolution using a compound scaling method. It achieves state-of-the-art accuracy with improved efficiency.
7️⃣ NASNet: Leverages neural architecture search to automatically design efficient CNN architectures. It often outperforms manually designed models in terms of accuracy and efficiency.
@Machine_learn
🌟 RLtools
🟢TD3 - Pendulum, Racing Car, MuJoCo Ant-v4, Acrobot;
🟢PPO - Pendulum, Racing Car, MuJoCo Ant-v4 (CPU), MuJoCo Ant-v4 (CUDA);
🟢Multi-Agent PPO - Bottleneck;
🟢SAC - Pendulum (CPU), Pendulum (CUDA), Acrobot.# Clone and checkout
git clone https://github.com/rl-tools/example
cd example
git submodule update --init external/rl_tools
# Build and run
mkdir build
cd build
cmake .. -DCMAKE_BUILD_TYPE=Release
cmake --build .
./my_pendulum
🟡Arxiv
🟡RLTools Design Studio
🟡Demo
🟡Zoo Experiment Tracking
🟡Google Collab (Python Interface)
🖥GitHub
@Machine_learn
با عرض سلام
اولين مقاله ي LLM ما در مرحله ي سابميت. نفر چهارم قابل اضافه كردن مي باشد. جهت مشاركت به ايدي بنده مراجعه كنين.
ExKG-LLM: Leveraging Large Language Models for Automated Expan-
sion of Cognitive Neuroscience Knowledge Graphs
Abstract
Objective: This paper introduces ExKG-LLM, an innovative framework designed to automate expanding cognitive neuroscience knowledge graphs (CNKG) using large-scale linguistic models (LLM). This model includes increasing knowledge graphs’ accuracy, completeness and usefulness in cognitive neuroscience.
Method: To address the limitations of existing tools for creating knowledge accounts, this is especially true in dealing with the complex hierarchical relationships within the cognitive neuroscience literature. We use a large dataset of scientific paper and clinical reports, the ExKG-LLM framework, new entities and relationships in CNKG to apply state - state of the art LLM to extract, optimize and integrate, evaluating performance based on
metrics such as precision, recall and graph density.
Findings: The ExKG-LLM framework achieved significant improvements, including precision of 0.80 (increase of 6.67%), recall of 0.81 (increase of 15.71%), F1 score of 0.805 (increase of 11.81%), and number of edge nodes increased by 21.13% and 31.92%, respectively. Also, the density of the graph decreased slightly. Reflecting the broader but more fragmented structure, engagement rates have also increased by 20%, highlighting areas where stability needs improvement. From the perspective of a complex network, increasing the diameter of CNKG to 15 compared to 13 shows that although the size of ExKG-LLM has increased, more steps are now required to discover additional nodes.Although time complexity improved to 𝑂(𝑛log 𝑛), space complexity became less efficient, rising to 𝑂(𝑛2), indicating higher memory usage for managing the expanded
graph.
journal: https://www.inderscience.com/jhome.php?jcode=ijdmb
هزينه مشاركت ١٢ ميليون
@Raminmousa
@Machine_learn
/channel/+SP9l58Ta_zZmYmY0
Approaching (Almost) Any Machine Learning Problem
#Book
#ML
@Machine_learn
New research papers and github codes
🟢Motivo
🟡Paper 🟡Demo 🟡Github
🟢Video Seal
🟡Paper 🟡Demo 🟡Github
🟢Flow Matching
🟡Paper 🟡Github
🟢Explore Theory-of-Mind
🟡Paper 🟡Github 🟡Dataset
🟢Large Concept Model (LCM)
🟡Paper 🟡Github
🟢Dynamic Byte Latent Transformer
🟡Paper 🟡Github
🟢Memory Layers.
🟡Paper 🟡Github
🟢EvalGym
🟡Paper 🟡Github
🟢CLIP 1.2
🟡Paper 🟡Github 🟡Dataset 🟡Model
@Machine_learn
با عرض سلام در راستاي ادامه تحقيقات مشترك سعي داريم روي حوزه ي LLM مدل ها كار كنيم.
این کار تحت نظر استاد
Rex (Zhitao) Ying
انجام میشه.
link: https://scholar.google.com.au/citations?user=6fqNXooAAAAJ&hl=en
۲نفر براي همکاری نياز داريم.
BioPars: a pre-trained biomedical large language model for persian biomedical text mining.
١- مراحل اوليه: جمع اوري متن هاي فارسي بيولوژيكي از منابع (...)
٢- پيش پردازش متن ها و تميز كردن متن ها
٣- اموزش ترنسفورمرها ي مورد نظر
٤- استفاده از بردارها ي اموزش داده شده در سه تسك (...)
دوستاني كه مايل به مشاركت هستن مي تونين بهم اطلاع بدن.
هزينه سرور به ازاي هر ساعت ١.٢ دلار مي باشد. و حدود ٢ هزار ساعت براي اموزش مدل زباني نياز ميباشد. هزينه به ترتيب براي نفرات علاوه بر انجام تسك ها به صورت زير مي باشد.
🔹نفر سوم 500 دلار
🔺نفر چهارم 400 دلار
@Raminmousa
@Machine_learn
/channel/+SP9l58Ta_zZmYmY0
🌟 AlphaFold 3
🟡Paper
🟡Demo
🖥GitHub
@Machine_learn
📑 Application of graph theory in liver research: A review
📎 Study paper
@Machine_learn
Probability, Random Processes, and Statistical Analysis Applications to Communications, Signal Processing, Queueing Theory and Mathematical Finance
📕 Book
@Machine_learn
Time Series Visualization from Raw Data to Insights
🔹 #Code
@Machine_learn
امشب اخرین فرصت برای مشارکت در این مقاله هستش...!🔸🔸
Читать полностью…
Lecture notes: mathematics for artificial intelligence
📕 Link
@Machine_learn
Arcade Academy - Learn Python
📖 Book
@Machine_learn
KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation
Paper: https://arxiv.org/pdf/2409.13731v3.pdf
Code: https://github.com/openspg/kag
Dataset: 2WikiMultiHopQA
🔸@Machine_learn
Large Language Models Course: Learn by Doing LLM Projects
🖥 Github: https://github.com/peremartra/Large-Language-Model-Notebooks-Course
📕 Paper: https://doi.org/10.31219/osf.io/qgxea
@Machine_learn
با عرض سلام اخرين فرصت مشاركت در اين مقاله تا فردا شب...!
Читать полностью…
📌 Convex Optimization
Book
@Machine_learn
Text-to-Image Generation with GANs
#GANs
@Machine_learn
با عرض سلام
اولين مقاله ي LLM ما در مرحله ي سابميت. نفر چهارم قابل اضافه كردن مي باشد. جهت مشاركت به ايدي بنده مراجعه كنين.
ExKG-LLM: Leveraging Large Language Models for Automated Expan-
sion of Cognitive Neuroscience Knowledge Graphs
Abstract
Objective: This paper introduces ExKG-LLM, an innovative framework designed to automate expanding cognitive neuroscience knowledge graphs (CNKG) using large-scale linguistic models (LLM). This model includes increasing knowledge graphs’ accuracy, completeness and usefulness in cognitive neuroscience.
Method: To address the limitations of existing tools for creating knowledge accounts, this is especially true in dealing with the complex hierarchical relationships within the cognitive neuroscience literature. We use a large dataset of scientific paper and clinical reports, the ExKG-LLM framework, new entities and relationships in CNKG to apply state - state of the art LLM to extract, optimize and integrate, evaluating performance based on
metrics such as precision, recall and graph density.
Findings: The ExKG-LLM framework achieved significant improvements, including precision of 0.80 (increase of 6.67%), recall of 0.81 (increase of 15.71%), F1 score of 0.805 (increase of 11.81%), and number of edge nodes increased by 21.13% and 31.92%, respectively. Also, the density of the graph decreased slightly. Reflecting the broader but more fragmented structure, engagement rates have also increased by 20%, highlighting areas where stability needs improvement. From the perspective of a complex network, increasing the diameter of CNKG to 15 compared to 13 shows that although the size of ExKG-LLM has increased, more steps are now required to discover additional nodes.Although time complexity improved to 𝑂(𝑛log 𝑛), space complexity became less efficient, rising to 𝑂(𝑛2), indicating higher memory usage for managing the expanded
graph.
journal: https://www.inderscience.com/jhome.php?jcode=ijdmb
@Raminmousa
@Machine_learn
/channel/+SP9l58Ta_zZmYmY0
دوستان خروجي اين كار ٣ تا مقاله خواهد بود...!
Читать полностью…
🌟 LLaMA-Mesh:
🟡Arxiv
🖥GitHub
/channel/deep_learning_proj
Building Blocks for Theoretical Computer Science
🎓 Link
@Machine_learn
با عرض سلام مقاله زیر در مرحله major revision می‌باشد. نفر ۴ ام از این مقاله قابل اضافه کردن است.
Abstract
Breast cancer stands as a prevalent cause of fatality among females on a global scale, with
prompt detection playing a pivotal role in diminishing mortality rates. The utilization of
ultrasound scans in the BUSI dataset for medical imagery pertaining to breast cancer has
exhibited commendable segmentation outcomes through the application of UNet and UNet++
networks. Nevertheless, a notable drawback of these models resides in their inattention towards
the temporal aspects embedded within the images. This research endeavors to enrich the
UNet++ architecture by integrating LSTM layers and self-attention mechanisms to exploit
temporal characteristics for segmentation purposes. Furthermore, the incorporation of a
Multiscale Feature Extraction Module aims to grasp varied scale features within the UNet++.
Through the amalgamation of our proposed methodology with data augmentation on the BUSI
with GT dataset, an accuracy rate of 98.88%, specificity of 99.53%, precision of 95.34%,
sensitivity of 91.20%, F1-score of 93.74, and Dice coefficient of 92.74% are achieved. These
findings demonstrate competitiveness with cutting-edge techniques outlined in existing
literature.
Keywords: Attention mechanisms, BUSI dataset, Deep Learning, Feature Extraction,
Multi-Scale features
دوستانی که نیاز دارن به ایدی بنده پیام بدن.
#Unet++
#Segmentation
@Raminmousa
@Machine_learn
/channel/+SP9l58Ta_zZmYmY0
Book: The Art of Data Science
Authors: Roger D. Peng & Elizabeth Matsui
@Machine_learn
New o3 OpenAI model is changing the game!
For a long time, ARC was seen as proof that AI models “can’t think.” The argument went: if they truly could, why do they perform so poorly on this benchmark?
Well, those days are over. The o3 model demonstrates not only the ability to think but also the capability to tackle tasks once considered out of reach.
👀 Check out the full breakdown of this breakthrough: https://arcprize.org/blog/oai-o3-pub-breakthrough
It might be time to rethink what AI can achieve. Looking forward to the release!
@Machine_learn