
נעמי פרידמן
M.Sc Mathematics. MS.c Computer science. Deep learning , Machine learning and Data Science
Tel Aviv-Yafo, Israel
Freelancer
ABOUT
Deep Learning and Machine Learning consutent
MSc Applied Mathematics.Technion Haifa.
BSc Mathematics, Philosophy, Computer science. TLV University.
MSc Computer scince. Afeka College of Engineering.
MSc Applied Mathematics.Technion Haifa.
BSc Mathematics, Philosophy, Computer science. TLV University.
MSc Computer scince. Afeka College of Engineering.
LANGUAGES
Hebrew
Native or bilingual proficiency
English
Full professional proficiency
Russian
Elementary proficiency
SKILL DETAILS
Training
650 ₪
/ hr
Machine Learning Training
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Technology
650 ₪
/ hr
AI, Artificial Intelligence
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Data Scientist , Deep learning, Machine learning .Self-Employed and Research assistant at Sheba Hospital.
Looking for interesting ML and DL projects.
Education:
Mc Applied Mathematics Technion Haifa.
Bsc Mathematics, Philosophy, Computer science, TLV university.
More about me:
` https://www.kaggle.com/ripcurl
- https://www.linkedin.com/in/naomi-fridman/
- https://github.com/naomifridman
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Data Scientist , Deep learning, Machine learning .Self-Employed and Research assistant at Sheba Hospital.
Looking for interesting ML and DL projects.
Education:
Mc Applied Mathematics Technion Haifa.
Bsc Mathematics, Philosophy, Computer science, TLV university.
More about me:
` https://www.kaggle.com/ripcurl
- https://www.linkedin.com/in/naomi-fridman/
- https://github.com/naomifridman
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
Machine Learning
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Developing machine learning models
https://www.kaggle.com/ripcurl
https://github.com/naomifridman
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Developing machine learning models
https://www.kaggle.com/ripcurl
https://github.com/naomifridman
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
Image Processing
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
** M.SC APPLIED MATHEMATICS TECHNION HAIFA, Com Laude
Thesis: Computer vision, pattern recognition algorithm.
Article: The canonical coordinates method for pattern recognition.
Isomorphisms with affine transformations
https://www.sciencedirect.com/science/article/pii/0031320394900205
** SOFTWARE ENGINEER AND APPLICATION TEAM LEADER,
TILTAN TECHNOLOGIES
Key developments: computer vision mosaic application that connect and complete the seam lines between
aerial or satellite images, to create Continuous mapping image.
used to build 3D geographical models.
** SHEBA
Developed deep learning algorithms for image segmentation.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
** M.SC APPLIED MATHEMATICS TECHNION HAIFA, Com Laude
Thesis: Computer vision, pattern recognition algorithm.
Article: The canonical coordinates method for pattern recognition.
Isomorphisms with affine transformations
https://www.sciencedirect.com/science/article/pii/0031320394900205
** SOFTWARE ENGINEER AND APPLICATION TEAM LEADER,
TILTAN TECHNOLOGIES
Key developments: computer vision mosaic application that connect and complete the seam lines between
aerial or satellite images, to create Continuous mapping image.
used to build 3D geographical models.
** SHEBA
Developed deep learning algorithms for image segmentation.
Neural Networks
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
https://github.com/naomifridman
https://www.kaggle.com/ripcurl
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
https://github.com/naomifridman
https://www.kaggle.com/ripcurl
Speech, Voice Recognition
Deep Learning
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
Github:
* Deep-VAE-prediction-of-churn-customer Variational deep autoencoder to predict churn customer
* Neural-Network-Churn-Prediction Deep Learning: Feedforward Neural Network for churn prediction
* SoiRecTimeSeries R toy project of Time series statistical analysis and visualization, with SOI and REC data sets
* Top-N-Words-In-Tweets-Google-Cloud Python Java Haddop
https://github.com/naomifridman
https://www.kaggle.com/ripcurl
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
Github:
* Deep-VAE-prediction-of-churn-customer Variational deep autoencoder to predict churn customer
* Neural-Network-Churn-Prediction Deep Learning: Feedforward Neural Network for churn prediction
* SoiRecTimeSeries R toy project of Time series statistical analysis and visualization, with SOI and REC data sets
* Top-N-Words-In-Tweets-Google-Cloud Python Java Haddop
https://github.com/naomifridman
https://www.kaggle.com/ripcurl
Software & Programming
650 ₪
/ hr
BI, Data Science, Big Data
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Developed ML and DL algorithms
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data,and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
Github:
* Deep-VAE-prediction-of-churn-customer Variational deep autoencoder to predict churn customer
* Neural-Network-Churn-Prediction Deep Learning: Feedforward Neural Network for churn prediction
* SoiRecTimeSeries R toy project of Time series statistical analysis and visualization, with SOI and REC data sets
* Top-N-Words-In-Tweets-Google-Cloud Python Java Haddop
https://github.com/naomifridman
https://www.kaggle.com/ripcurl
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Developed ML and DL algorithms
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data,and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
Github:
* Deep-VAE-prediction-of-churn-customer Variational deep autoencoder to predict churn customer
* Neural-Network-Churn-Prediction Deep Learning: Feedforward Neural Network for churn prediction
* SoiRecTimeSeries R toy project of Time series statistical analysis and visualization, with SOI and REC data sets
* Top-N-Words-In-Tweets-Google-Cloud Python Java Haddop
https://github.com/naomifridman
https://www.kaggle.com/ripcurl
Python
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Machine Learning and Deep Learning Algorithms.
Github:
Github:
* Deep-VAE-prediction-of-churn-customer Variational deep autoencoder to predict churn customer
* Neural-Network-Churn-Prediction Deep Learning: Feedforward Neural Network for churn prediction
* SoiRecTimeSeries R toy project of Time series statistical analysis and visualization, with SOI and REC data sets
* Top-N-Words-In-Tweets-Google-Cloud Python Java Haddop
https://github.com/naomifridman
https://www.kaggle.com/ripcurl
https://www.kaggle.com/ripcurl
https://github.com/naomifridman
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
Machine Learning and Deep Learning Algorithms.
Github:
Github:
* Deep-VAE-prediction-of-churn-customer Variational deep autoencoder to predict churn customer
* Neural-Network-Churn-Prediction Deep Learning: Feedforward Neural Network for churn prediction
* SoiRecTimeSeries R toy project of Time series statistical analysis and visualization, with SOI and REC data sets
* Top-N-Words-In-Tweets-Google-Cloud Python Java Haddop
https://github.com/naomifridman
https://www.kaggle.com/ripcurl
https://www.kaggle.com/ripcurl
https://github.com/naomifridman
Algorithm Development
בעלת תואר שני במתמטיקה שימושית ,טכניון.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
1999-2004
SOFTWARE ENGINEER, ALGORITHM DEVELOPER
MODELITY
http://www.modelity.com
Key developments: Algorithm to calculate Front efficient curve of investment portfolio (Markowitz curve).
Developed Algorithm that can manage portfolio which follows an economical index using genetic algorithms.
1993-1999
SOFTWARE ENGINEER AND APPLICATION TEAM LEADER,
TILTAN TECHOLOGIES
http://www.tiltan-se.co.il
Key developments: computer vision mosaic application that connect and complete the seam lines between
aerial or satellite images, to create Continuous mapping image.
used to build 3D geographical models.
בעלת תואר שני במערכות תבוניות cאפקה.
מומחית בלמידה עמוקה. בעלת ניסיון עשיר בתחום הבריאות.
בעלת ניסיון עשיר בפתרונות בינה מלאכותית של תמונות, וידאו, אותות, סריקות MRI, וכדומה.
ASSISTANT RESERCHER, SHEBA TEL HASHOMER
Deep learning to detect and predict cancer evolvement from sequential MRI images.
Since labeling MRI data requires excessive resources, I participated in 2 data since:
Competitions that offer high quality, aurally labeled divers medical data:
• Multimodal Brain Tumor Segmentation Challenge 2017.
The problem is a segmentation of 4 levels of cancer in MRI images.
Data and Results samples added below.
https://www.med.upenn.edu/sbia/brats2017/data.html
• 2018 Data Science Bowl, (Top 11 %)
The problem is a segmentation problem of nuclei in divergent microscope images.
https://www.kaggle.com/c/data-science-bowl-2018
Environment: Python, Keras, Theano, Nvidia GPU.
FREELANCE PROJECT
Churn prediction project for a big media company.
The project included modeling and engineering of large amount of usage data, and
Budding prediction models to identity the churn population.
Project code: https://github.com/naomifridman/Deep-VAE-prediction-of-churn-customer.
Environment: Python, Keras, Theano, Tensorflow, Amazon Cloud
Currently developing my TensorFlow abilities.
1999-2004
SOFTWARE ENGINEER, ALGORITHM DEVELOPER
MODELITY
http://www.modelity.com
Key developments: Algorithm to calculate Front efficient curve of investment portfolio (Markowitz curve).
Developed Algorithm that can manage portfolio which follows an economical index using genetic algorithms.
1993-1999
SOFTWARE ENGINEER AND APPLICATION TEAM LEADER,
TILTAN TECHOLOGIES
http://www.tiltan-se.co.il
Key developments: computer vision mosaic application that connect and complete the seam lines between
aerial or satellite images, to create Continuous mapping image.
used to build 3D geographical models.
EMPLOYMENT HISTORY
Today
Research assistant at Sheba Hospital.
SHEBA- ASSISTANT RESERCHER, SHEBA TEL HASHOMER
- Deep learning to detect and predict cancer evolvement from sequential MRI images.
- Since labeling MRI data requires excessive resources, I participated in 2 data since:
- Competitions that offer high quality, aurally labeled divers medical data:
- • Multimodal Brain Tumor Segmentation Challenge 2017.
- The problem is a segmentation of 4 levels of cancer in MRI images.
- Data and Results samples added below.
- https://www.med.upenn.edu/sbia/brats2017/data.html
- • 2018 Data Science Bowl, (Top 11 %)
- The problem is a segmentation problem of nuclei in divergent microscope images.
- https://www.kaggle.com/c/data-science-bowl-2018
- Environment: Python, Keras, Theano, Nvidia GPU.
March
2019
-
January
2021
deep learning consultent
philips, נתניה- זיהוי תהליכים רפואיים בווידאו של צנתור.
COURSES & CERTIFICATIONS
March
2016
Machine Learning Foundations: A Case Study Approach
Coursera- https://www.coursera.org/account/accomplishments/verify/G57JBRLTTWXN
January
2016
Introduction to Recommender Systems
Coursera- https://www.coursera.org/account/accomplishments/verify/EV5HPHZB6WS6
December
2015
Machine Learning
Coursera- https://www.coursera.org/account/accomplishments/verify/9STVG76X3GLP
EDUCATION
Today
Msc
Afeka- Subjects: Machine Learning, Deep Learning, Statistics
- At the last semester of this degree.
1988
-
1991
FIRST DEGREE IN COMPUTER SINCE
TEL AVIV UNIVERSITY- Completion of First degree in Computer science.
1988
-
1991
Msc
Technion Haifa- M.SC APPLIED MATHEMATICS
- TECHNION HAIFA, Com Laude
- Thesis: Computer vision, pattern recognition algorithm.
- Article: The canonical coordinates method for pattern recognition.
- Isomorphisms with affine transformations
- https://www.sciencedirect.com/science/article/pii/0031320394900205
ARMED FORCES
1983
-
1985
Air force
LINKS
github.com/naomifridman
naomifridman (naomi fridman)
naomifridman
* Deep-VAE-prediction-of-churn-customer
Variational deep autoencoder to predict churn customer
* Neural-Network-Churn-Prediction
Deep Learning: Feedforward Neural Network for churn prediction
* Neural-Network-Churn-Prediction
Deep Learning: Feedforward Neural Network for churn prediction
* SoiRecTimeSeries
R toy project of Time series statistical analysis and visualization, with SOI and REC data sets
* Top-N-Words-In-Tweets-Google-Cloud
Python Java Haddop