Mohammad K. Ebrahimpour, PhD

AI ML Scientist @ Apple. E-mail: mebrahimpour [@] ucmerced [DOT] edu

About me

I earned my Ph.D. from the University of California, Merced in 2020, under the mentorship of Prof. David C. Noelle. Prior to this, I completed my academic journey with a B.Sc. and M.Sc. in computer engineering and artificial intelligence from Shahid Bahonar University of Kerman, Iran (SBUK) in 2013 and 2015, respectively. My recent research has been centered on Generative AI and its applications on Large Language Models (LLM). In the past, my work spanned diverse areas, including object detection, fast similarity search, deep metric learning, 3D perception, voice to mesh, and auditory object recognition. Additionally, I have a keen interest in topics such as dimensionality reduction, feature selection, and combinatorial optimization. For a comprehensive overview of my academic and professional background, please refer to my concise CV.

Research

My research interests include:

• Generative AI

• LLM

• 3D Perception

• Deep Metric Learning

• Auditory Object Recognition

• Object Detection

• Deep Learning

• Machine Learning

• Feature Selection

• Ensemble Learning

Find out more.

Professional Appointments

• Apple - AI/ML Scientist (Dec 2023, Now).

• Ericsson Inc. - Senior Research Scientist (May 2021 - Dec 2023).

• ObjectVideo Labs - Alarm.com - Research Scientist (May 2020 - May 2021).

• Accenture Labs - Research Scientist (Aug 2019 - April 2020)

• Ancestry Inc. - Computer Vision Scientist (May 2018 - Aug 2018).

Recent Publications

• Deep Metric Learning

1. F. Saberi Movahed, M.K. Ebrahimpour, F. Saberi-Movahed, M. Moshavash, D. Rahmatian, M. Mohazzebi, M. Shariatzadeh, M. Eftekhari,‘‘Deep Metric Learning with Soft Orthogonal Proxies", /In BayLearn 2023.
   [paper] [longer version]

2. M.K.Ebrahimpour, G.Qian, A.Beach, ‘‘Multi-Head Deep Metric Learning Using Global and Local Representations’’, In WACV 2022.
   [paper] [longer version]

• Auditory Object Recognition

1. M.K.Ebrahimpour, S.Schneider, D.C.Noelle, C.Kello, ‘‘Infantnet: A deep neural network for analyzing infant vocalizations’’ , In arXiv 2020.
   [paper]

2. M.K.Ebrahimpour, T.M.Shea, A.Danielescu, D.C.Noelle, C.Kello, ‘‘End-to-End Auditory Object Recognition on Neuromorpic hardware chip’’, In TinyML 2020.
   [paper]

3. M.K.Ebrahimpour, T.M.Shea, A.Danielescu, D.C.Noelle, C.Kello, ‘‘End-to-End Auditory Object Recognition via Inception Nucleus’’, In ICASSP 2020.
   [paper]

• Object Detection

1. M.K.Ebrahimpour, J.B. Falandays, S.Spevack, M.H.Yang, D.C.Noelle, ‘‘WW-Nets: Dual Neural Networks for Object Detection’’, In IJCNN 2020.
   [paper]

2. M.K.Ebrahimpour, J.B.Falandays, S.Spevack, D.C.Noelle, ‘‘Do Humans Look Where Deep Convolutional Neural Networks ‘Attend’ ’’?, In CogSci 2019.
   [paper]

3. M.K.Ebrahimpour, D.C.Noelle, ‘‘Fast Object Localization via Sensitivity Analysis’’, In ISVC 2019.
   [paper]

4. M.K.Ebrahimpour, J.B.Falandays, S.Spevack, D.C.Noelle, ‘‘Do Humans Look Where Deep Convolutional Neural Networks ‘Attend’ ’’?, In ISVC 2019.
   [paper]

5. J.Li, M.K.Ebrahimpour, Y.Y.Yu, ‘‘Image Captioning with Weakly-Supervised Attention Penalty’’, In CVPRW 2019.
   [paper]

6. M.K.Ebrahimpour, J.Li, Y.Y.Yu, J.Reese, A.Moghtaderi, M.H,Yang, D.C. Noelle, ‘‘Ventral-Dorsal Networks: Object Detection via Selective Attention’’, In WACV 2019.
   [paper][implementation]

7. M.K.Ebrahimpour, D.C.Noelle, ‘‘Weakly Supervised Object Localization via Sensitivity Analysis’’, In CVPRW 2018.
   [paper]

• Optimization

1. M.K.Ebrahimpour, H.Nezamabadi-pour, M.Eftekhari, ‘‘CCFS: A Cooperation Coevolution Techniques for Large Scale Feature Selection on Microarray Datasets’’, In Computational Biology and Chemistry 2017.
   [paper][implementation]

• Dimensionality Reduction

1. M.K.Ebrahimpour, H.Mirvaziri, and V.Sattari-Naeini, ‘‘Improving Breast Cancer Classification by Dimensional Reduction on Mammograms’’, In Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization 2017.
   [paper] [implementation]

• Feature Selection

1. M.K.Ebrahimpour, M.Eftekhari, ‘‘MCMR: Maximum Consistency Minimum Redundancy for Microarray High-Dimensional Feature Selection’’, In Pattern Recognition 2017
   [paper]

2. M.K.Ebrahimpour, M.Eftekhari, ‘‘Distributed Feature Selection: A Hesitant Fuzzy Correlation Concept for Microarray High-Dimensional Datasets’’, In Chemometrics and Intelligent Laboratory Systems 2018.
   [paper][implementation]
   

3. M.K.Ebrahimpour, M.Eftekhari, ‘‘Occam’s Razor in Dimension Reduction: Using Reduced Row Echelon Form for Finding Linear Independent Features for High Dimensional Feature Selection’’, In Engineering Applications of Artificial Intelligence 2017.
   [paper][implementation]
   

4. M.K.Ebrahimpour, M.Eftekhari, ‘‘Ensemble of Feature Subset Selection Methods: A Hesitant Fuzzy Set Approach’’, In Applied Soft Computing 2017.
   [paper][implementation]
   

5. M.K.Ebrahimpour, M.Eftekari, ‘‘Feature Subset selection using Information Energy and correlation coefficients of hesitant fuzzy sets’’, InInternational Conference on Information and Knowledge Technology (IKT 2015).
   [paper]
   

6. M.K.Ebrahimpour, M.Eftekhari, ‘‘Proposing a Novel Feature Selection Algorithm based on Hesitant Fuzzy Sets and Correlation Concepts’’, In Artificial Intelligence and Signal Processing (AISP 2015).
   [paper]
   

• Ensemble Learning

1. N.A.Abolkarlou, A.A.Niknafs, M.K.Ebrahimpour, ‘‘Ensemble Imbalanced Classification: Using Data Preprocessing, Clustering Algorithm and Genetic Algorithm’’, In Computer and Knowledge Engineering (ICCKE 2014).
   [paper]
   

2. N.Afshari, M.K.Ebrahimpour, A.A.Niknafs, ‘‘Improving the Ensemble Classifiers based on Clustering Approaches and Genetic Algorithm’’, In International conference on information Technology and Computer 2014.
   Full list of publications.