Graph Neural Network for VLSI placement Optimization
Budget: $750 – $1,500 USD
Project Description:
We are seeking a skilled machine learning expert with experience in graph neural networks (GNNs) and VLSI design to develop a model for predicting placement representation in VLSI floor planning.
Here is the Project Scope:
Data Preparation:
1. Utilize a dataset consisting of approximately 300 graphs representing VLSI designs.
2. Each graph has an expected representation that indicates the optimal placement of subcircuits.
Model Development:
1. Design and implement a graph neural network using Python frameworks such as TensorFlow or PyTorch.
2. The model should be capable of learning from the provided graphs and predicting the representation.
Training and Validation:
1. Split the dataset into training and validation sets.
2. Train the GNN model on the training set and validate its performance on the validation set.
3. Implement performance metrics to evaluate the accuracy and efficiency of the model.
Optimization and Fine-Tuning:
Optimize the model for best performance.
1. Fine-tune hyperparameters to improve prediction accuracy.
Documentation and Reporting:
1. Provide detailed documentation of the model architecture, training process, and results.
2. Deliver a final report summarizing the project outcomes and model performance.
Deliverables:
1. A fully functional graph neural network model for predicting representation in VLSI floorplanning.
2. Python codebase with clear documentation.
3. Training and validation datasets used in the project.
4. Final report detailing the project, including model architecture, training process, performance metrics, and results.
Requirements:
1. Proven experience in developing machine learning models, specifically graph neural networks.
2. Strong knowledge of Python and relevant libraries (TensorFlow, PyTorch, NetworkX, etc.).
3. Understanding of VLSI design and floorplanning concepts is a plus.
4. Ability to deliver high-quality, well-documented code and reports.
5. Good communication skills for regular updates and collaboration.
Timeline:
The expected timeline for project completion is 8 weeks. Please outline your proposed timeline and any milestones.
How to Apply:
Interested freelancers are invited to submit their proposals, including:
1. A brief overview of their experience with similar projects.
2. Examples of previous work, particularly involving GNNs and/or VLSI design.
3. Proposed approach for this project.
4. Estimated cost and timeline.
5. Share you public github repository containing code base which you may have worked on in the past.
You should be ready to attend a call when asked to do.
We are seeking a skilled machine learning expert with experience in graph neural networks (GNNs) and VLSI design to develop a model for predicting placement representation in VLSI floor planning.
Here is the Project Scope:
Data Preparation:
1. Utilize a dataset consisting of approximately 300 graphs representing VLSI designs.
2. Each graph has an expected representation that indicates the optimal placement of subcircuits.
Model Development:
1. Design and implement a graph neural network using Python frameworks such as TensorFlow or PyTorch.
2. The model should be capable of learning from the provided graphs and predicting the representation.
Training and Validation:
1. Split the dataset into training and validation sets.
2. Train the GNN model on the training set and validate its performance on the validation set.
3. Implement performance metrics to evaluate the accuracy and efficiency of the model.
Optimization and Fine-Tuning:
Optimize the model for best performance.
1. Fine-tune hyperparameters to improve prediction accuracy.
Documentation and Reporting:
1. Provide detailed documentation of the model architecture, training process, and results.
2. Deliver a final report summarizing the project outcomes and model performance.
Deliverables:
1. A fully functional graph neural network model for predicting representation in VLSI floorplanning.
2. Python codebase with clear documentation.
3. Training and validation datasets used in the project.
4. Final report detailing the project, including model architecture, training process, performance metrics, and results.
Requirements:
1. Proven experience in developing machine learning models, specifically graph neural networks.
2. Strong knowledge of Python and relevant libraries (TensorFlow, PyTorch, NetworkX, etc.).
3. Understanding of VLSI design and floorplanning concepts is a plus.
4. Ability to deliver high-quality, well-documented code and reports.
5. Good communication skills for regular updates and collaboration.
Timeline:
The expected timeline for project completion is 8 weeks. Please outline your proposed timeline and any milestones.
How to Apply:
Interested freelancers are invited to submit their proposals, including:
1. A brief overview of their experience with similar projects.
2. Examples of previous work, particularly involving GNNs and/or VLSI design.
3. Proposed approach for this project.
4. Estimated cost and timeline.
5. Share you public github repository containing code base which you may have worked on in the past.
You should be ready to attend a call when asked to do.