Ali Ghodsi
Professor, University of Waterloo
[first name].[last name] [AT] uwaterloo.ca
Ali Ghodsi is a Professor at the University of Waterloo, Director of the Data Science Lab, and a Faculty Affiliate at the Vector Institute. His research focuses on developing new methods and algorithms in machine learning and artificial intelligence, with particular interests in deep learning, large language models, and AI for scientific and mathematical discovery. His work explores how advances in learning algorithms can help address open problems in science, mathematics, and statistics.
He is the co-author of Elements of Deep Learning (Springer, 2026) and Elements of Dimensionality Reduction and Manifold Learning (Springer, 2024). Through his books and openly available university lectures, he also works to make advanced ideas in machine learning accessible to students, researchers, and practitioners.
Vitæ
Full Resume in PDF.
Prospective Students
We are currently recruiting PhD students in Statistics or Computer Science whose interests align with our work in machine learning and artificial intelligence. Exceptional postdoctoral researchers and visiting scholars are also welcome to apply.
Master's admissions: We are not currently accepting Master's students.
Interested in joining the Data Science Lab? Please submit the short application form.
Apply to the LabData Science Lab
The Data Science Lab brings together students and researchers developing new methods and algorithms in machine learning and artificial intelligence. The lab's current interests include deep learning, large language models, and AI for scientific and mathematical discovery, particularly approaches that can help address open problems in science, mathematics, and statistics.
Current Members
- Mahdi Karami — Senior Scientist, Research Scientist @ Google Research
- Alireza Ghadimi — PhD Student
- Aref Jafari — PhD Student
- Daniel Zhang — PhD Student
- Max Homm — Master's Student
- Kefah Alshaer — Master's Student
Alumni
- Lena Podina — Postdoctoral Fellow @ MIT
- Amin Ravanbakhsh — ML Engineer @ Huawei
- Mojtaba Moodi
- Zhang Ma — Software Developer @ Hammond Power Solutions
- Babak Alipanahi — Co-founder and CSO @ Exai Bio
- Tameem Adel — Assistant Professor @ University of Cambridge
- Pooyan Khajehpour Tadavoni — Software Engineer @ Google
- Ahmed Farahat — Principal Research Scientist @ Hitachi America
- Mehrdad Jabarzadeh Gangeh — Principal Imaging Scientist @ Roche
- Rui Qiao — Applied Scientist @ Amazon
- Maysum Panju — NLP Scientist @ Adeptmind
- Ershad Banijamali — Applied Scientist, Artificial General Intelligence @ Amazon
- Daniel Severn — PhD Graduate
- Mojtaba Valipour — Founding Engineer @ Coastal Carbon
- Amir-Hossein Karimi — Assistant Professor @ University of Waterloo
- Bowen You — Co-founder @ Fairblock
- Benyamin Jamialahmadi — NLP Research Scientist
- Maryam Yalsavar — Master’s Graduate
- Ali Saheb Pasand — Researcher @ Mila/McGill
- Amirreza Lashkari — AI Researcher @ Amazon
- Elnaz Barshan — Senior Machine Learning Engineer @ Google
- Jinchao Lin — Software Engineer @ Google
- Grace Yang — Software Engineer, Machine Learning @ Meta
- Fatemeh Dorri — Principal Bioinformatics Scientist @ Roche
- Trevor Sabourin — Family Physician
- Hadi Zarkoob — Senior Data Scientist @ Genalyte, Inc.
- Stefan Pintilie — Compiler Optimization Developer @ IBM
- Maryam Iraniparast — Data Analyst @ University of Waterloo
Teaching
Current Courses — Fall 2026
Previously Taught Courses
Deep Learning (STAT 940)
- Deep Learning, Motivation and course administrations - Slides (PDF)
- Feedforward Neural Network, Backpropagation - Slides (PDF)
- Optimization - Slides (PDF)
- Regularization - Slides (PDF)
- Dropout, Batch Normalization - Slides (PDF)
- Convolutional Neural Networks (CNN) - Slides (PDF)
- Regularization (Layer norm, FRN, TRU), Keras - Slides (PDF)
- Recurrent neural network (RNN) - Slides (PDF)
- Attention mechanism, self-attention, S2S - Slides (PDF)
- Transformers - Slides (PDF)
- BERT and GPT - Slides (PDF)
- Deep Reinforcement Learning (Part 1) - Slides (PDF)
- Deep Reinforcement Learning (Part 2) - Slides (PDF)
- RLHF, ChatGPT, Alignment in LLMs - Slides (PDF)
- Variational Autoencoder, VAE, Performer - Slides (PDF)
- Generative Adversarial Networks (GAN), AAE - Slides (PDF)
- Diffusion Models, DDPMs - Slides (PDF)
- Graph Neural Network (Part 1) - Slides (PDF)
- Graph Neural Network (Part 2) - Slides (PDF)
- PAC Learnability in Deep Learning - Slides (PDF)
For complete video lectures and additional materials, visit the comprehensive course page .
Supervised Learning (STAT 441/841)
- Intro to classifiers, Bayesian classifiers, LDA and QDA
- QDA, PCA
- FDA
- Logistic regression
- Model selection, Neural Networks
- Spectral Clustering, Laplacian Eigenmap, MVU
- Back Propagation, RBN
- Complexity control for RBN
- Regularization, Hard Margin SVM
- SVM, Kernel SVM
- Soft Margin SVM
- Metric Learning
- SPCA, Naive Bayes, K-nearest neighbour
- Convolutional Neural Networks
- Random features, Tree
- Tree, Boosting method
- Boosting method
- Bagging
For complete video lectures and additional materials, visit the comprehensive course page .
Unsupervised Learning (STAT 442/842)
- Principal Component Analysis
- PCA (Ordinary, Dual, Kernel)
- FDA
- MDS, Isomap, LLE
- LLE, Spectral Clustering
- Spectral Clustering, Laplacian Eigenmap, MVU
- MVU, Action Respecting Embedding, Supervised PCA
- Supervised PCA
- SPCA, Nystrom Approximation, NMF
- NMF via R1D algorithm
- Sum-Product Networks
- Neural Networks, Autoencoders, Word2Vec
- Word2Vec Skip-Gram
- Autoencoders, Clustering, Mixture of Gaussians
- t-SNE
- Variational Autoencoders
For complete video lectures and additional materials, visit the comprehensive course page .
Course Archive: Browse all videos, lecture slides, and course materials
Publications
Most recent publications on Google Scholar.
Auto-Regressive Masked Diffusion Models
Karami, Mahdi, Ghodsi, Ali
International Conference on Artificial Intelligence and Statistics (AISTATS), 2026
Learning chemotherapy drug action via universal physics-informed neural networks
Podina, Lena and Ghodsi, Ali and Kohandel, Mohammad
Pharmaceutical Research, 2025
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
Karami, Mahdi, Ghodsi, Ali
NeurIPS, 2024
GraphPI: Efficient Protein Inference with Graph Neural Networks
Ma, Zheng, Chen, Jiazhen, Xin, Lei, Ghodsi, Ali
Journal of Proteome Research, 2024
Qdylora: Quantized dynamic low-rank adaptation for efficient large language model tuning
Rajabzadeh, Hossein, Valipour, Mojtaba, Zhu, Tianshu, Tahaei, Marzieh, Kwon, Hyock Ju, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
emnlp-industry, 2024
Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification
Tahaei, Marzieh, Jafari, Aref, Rashid, Ahmad, Alfonso-Hermelo, David, Bibi, Khalil, Wu, Yimeng, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
Findings of the Association for Computational Linguistics: NAACL, 2024
Echoatt: Attend, copy, then adjust for more efficient large language models
Rajabzadeh, Hossein, Jafari, Aref, Sharma, Aman, Jami, Benyamin, Kwon, Hyock Ju, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
Efficient Natural Language and Speech Processing (ENLSP-IV) workshop, 2024
Systems and methods for de novo peptide sequencing using deep learning and spectrum pairs
Qiao, Rui, Tran, Ngoc Hieu, Lei, XIN, Chen, Xin, Baozhen, SHAN, Ghodsi, Ali, Li, Ming
, 2023
Do we need Label Regularization to Fine-tune Pre-trained Language Model
Kobyzev, Ivan, Jafari, Aref, Rezagholizadeh, Mehdi, Li, Tianda, Do-Omri, Alan, Lu, Peng, Ghodsi, Ali, Poupart, Pascal
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Kavehzadeh, Parsa, Valipour, Mojtaba, Tahaei, Marzieh, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
arXiv preprint arXiv:2309.08968, 2023
Continuation kd: Improved knowledge distillation through the lens of continuation optimization
Jafari, Aref, Kobyzev, Ivan, Rezagholizadeh, Mehdi, Poupart, Pascal, Ghodsi, Ali
Findings of the Association for Computational Linguistics: EMNLP 2022, 2022
Supervised discriminative dimensionality reduction by learning multiple transformation operators
Rajabzadeh, Hossein, Jahromi, Mansoor Zolghadri, Ghodsi, Ali
Expert Systems with Applications, 2021
CNN and deep sets for end-to-end whole slide image representation learning
Hemati, Sobhan, Kalra, Shivam, Meaney, Cameron, Babaie, Morteza, Ghodsi, Ali, Tizhoosh, Hamid
Medical Imaging with Deep Learning, 2021
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices
Qiao, Rui, Tran, Ngoc Hieu, Xin, Lei, Chen, Xin, Li, Ming, Shan, Baozhen, Ghodsi, Ali
Nature Machine Intelligence, 2021
Knowledge distillation by utilizing backward pass knowledge in neural networks
Jafari, Aref, Rezagholizadeh, Mehdi, Ghodsi, Ali
Efficient Natural Language and Speech Processing (ENLSP workshop), 2021
Annealing knowledge distillation
Jafari, Aref, Rezagholizadeh, Mehdi, Sharma, Pranav, Ghodsi, Ali
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 2021
How to select one among all? an extensive empirical study towards the robustness of knowledge distillation in natural language understanding
Li, Tianda, Rashid, Ahmad, Jafari, Aref, Sharma, Pranav, Ghodsi, Ali, Rezagholizadeh, Mehdi
Findings of the Association for Computational Linguistics: EMNLP 2021, 2021
Pro-KD: Progressive distillation by following the footsteps of the teacher
Rezagholizadeh, Mehdi, Jafari, Aref, Salad, Puneeth, Sharma, Pranav, Pasand, Ali Saheb, Ghodsi, Ali
Proceedings of the 29th International Conference on Computational Linguistics, 2022, 2021
Deep learning enables de novo peptide sequencing from data-independent-acquisition mass spectrometry
Tran, Ngoc Hieu, Qiao, Rui, Xin, Lei, Chen, Xin, Liu, Chuyi, Zhang, Xianglilan, Shan, Baozhen, Ghodsi, Ali, Li, Ming
Nature methods, 2019
Deepnovov2: Better de novo peptide sequencing with deep learning
Qiao, Rui, Tran, Ngoc Hieu, Xin, Lei, Shan, Baozhen, Li, Ming, Ghodsi, Ali
arXiv preprint arXiv:1904.08514, 2019
Robust locally-linear controllable embedding
Banijamali, Ershad, Shu, Rui, Bui, Hung, Ghodsi, Ali, others
International Conference on Artificial Intelligence and Statistics, 2018
Ensembles of random projections for nonlinear dimensionality reduction
Karimi, Amir Hossein, Shafiee, Mohammad Javad, Ghodsi, Ali, Wong, Alexander
Journal of Computational Vision and Imaging Systems, 2017
Minimizing the discrepancy between source and target domains by learning adapting components
Dorri, Fatemeh, Ghodsi, Ali
Journal of Computer Science and Technology, 2014
Adapting component analysis
Dorri, Fatemeh, Ghodsi, Ali
2012 IEEE 12th International Conference on Data Mining, 2012
An efficient greedy method for unsupervised feature selection
Farahat, Ahmed K, Ghodsi, Ali, Kamel, Mohamed S
2011 IEEE 11th International Conference on Data Mining, 2011
Robust locally linear embedding using penalty functions
Winlaw, Manda, Dehkordy, Leila Samimi, Ghodsi, Ali
The 2011 International Joint Conference on Neural Networks, 2011
Parameter selection for smoothing splines using Stein's unbiased risk estimator
Seifzadeh, Sepideh, Rostami, Mohammad, Ghodsi, Ali, Karray, Fakhreddine
The 2011 International Joint Conference on Neural Networks, 2011
Nonnegative matrix factorization via rank-one downdate
Biggs, Michael, Ghodsi, Ali, Vavasis, Stephen
Proceedings of the 25th International Conference on Machine learning, 2008
Subjective localization with action respecting embedding
Bowling, Michael, Wilkinson, Dana, Ghodsi, Ali, Milstein, Adam
Robotics Research: Results of the 12th International Symposium ISRR, 2007
Action respecting embedding
Bowling, Michael, Ghodsi, Ali, Wilkinson, Dana
Proceedings of the 22nd international conference on Machine learning, 2005
A novel greedy algorithm for Nystrom approximation
Farahat, Ahmed, Ghodsi, Ali, Kamel, Mohamed
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics,
Learning chemotherapy drug action via universal physics-informed neural networks
Podina, Lena and Ghodsi, Ali and Kohandel, Mohammad
Pharmaceutical Research, 2025
GraphPI: Efficient Protein Inference with Graph Neural Networks
Ma, Zheng, Chen, Jiazhen, Xin, Lei, Ghodsi, Ali
Journal of Proteome Research, 2024
A new approach to the numerical solution of Fredholm integral equations using least squares-support vector regression
Parand, K, Aghaei, Alireza Afzal, Jani, Mostafa, Ghodsi, Ali
Mathematics and Computers in Simulation, 2021
Supervised discriminative dimensionality reduction by learning multiple transformation operators
Rajabzadeh, Hossein, Jahromi, Mansoor Zolghadri, Ghodsi, Ali
Expert Systems with Applications, 2021
Fine-tuning and training of densenet for histopathology image representation using tcga diagnostic slides
Riasatian, Abtin, Babaie, Morteza, Maleki, Danial, Kalra, Shivam, Valipour, Mojtaba, Hemati, Sobhan, Zaveri, Manit, Safarpoor, Amir, Shafiei, Sobhan, Afshari, Mehdi, others
Medical image analysis, 2021
Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices
Qiao, Rui, Tran, Ngoc Hieu, Xin, Lei, Chen, Xin, Li, Ming, Shan, Baozhen, Ghodsi, Ali
Nature Machine Intelligence, 2021
Fractional Chebyshev deep neural network (FCDNN) for solving differential models
Hajimohammadi, Zeinab, Baharifard, Fatemeh, Ghodsi, Ali, Parand, Kourosh
Chaos, Solitons and Fractals, 2021
Discriminant component analysis via distance correlation maximization
Abdi, Lida, Ghodsi, Ali
Pattern Recognition, 2020
Sentiment analysis based on improved pre-trained word embeddings
Rezaeinia, Seyed Mahdi, Rahmani, Rouhollah, Ghodsi, Ali, Veisi, Hadi
Expert Systems with Applications, 2019
Deep learning enables de novo peptide sequencing from data-independent-acquisition mass spectrometry
Tran, Ngoc Hieu, Qiao, Rui, Xin, Lei, Chen, Xin, Liu, Chuyi, Zhang, Xianglilan, Shan, Baozhen, Ghodsi, Ali, Li, Ming
Nature methods, 2019
Advances in projection of climate change impacts using supervised nonlinear dimensionality reduction techniques
Sarhadi, Ali, Burn, Donald H, Yang, Ge, Ghodsi, Ali
Climate dynamics, 2017
Fast and scalable feature selection for gene expression data using hilbert-schmidt independence criterion
Gangeh, Mehrdad J, Zarkoob, Hadi, Ghodsi, Ali
IEEE/ACM transactions on computational biology and bioinformatics, 2017
Sparse supervised principal component analysis (SSPCA) for dimension reduction and variable selection
Sharifzadeh, Sara, Ghodsi, Ali, Clemmensen, Line H, Ersbll, Bjarne K
Engineering Applications of Artificial Intelligence, 2017
Ensembles of random projections for nonlinear dimensionality reduction
Karimi, Amir Hossein, Shafiee, Mohammad Javad, Ghodsi, Ali, Wong, Alexander
Journal of Computational Vision and Imaging Systems, 2017
Greedy column subset selection for large-scale data sets
Farahat, Ahmed K, Elgohary, Ahmed, Ghodsi, Ali, Kamel, Mohamed S
Knowledge and Information Systems, 2015
Minimizing the discrepancy between source and target domains by learning adapting components
Dorri, Fatemeh, Ghodsi, Ali
Journal of Computer Science and Technology, 2014
Efficient greedy feature selection for unsupervised learning
Farahat, Ahmed K, Ghodsi, Ali, Kamel, Mohamed S
Knowledge and information systems, 2013
Kernelized supervised dictionary learning
Gangeh, Mehrdad J, Ghodsi, Ali, Kamel, Mohamed S
IEEE Transactions on Signal Processing, 2013
Discriminative functional analysis of human movements
Samadani, Ali-Akbar, Ghodsi, Ali, Kulic
Pattern Recognition Letters, 2013
Supervised principal component analysis: Visualization, classification and regression on subspaces and submanifolds
Barshan, Elnaz, Ghodsi, Ali, Azimifar, Zohreh, Jahromi, Mansoor Zolghadri
Pattern Recognition, 2011
Guided locally linear embedding
Alipanahi, Babak, Ghodsi, Ali
Pattern recognition letters, 2011
Automatic basis selection techniques for RBF networks
Ghodsi, Ali, Schuurmans, Dale
Neural Networks, 2003
Automatic dimensionality selection from the scree plot via the use of profile likelihood
Zhu, Mu, Ghodsi, Ali
Computational Statistics and Data Analysis,
Elements of dimensionality reduction and manifold learning
Ghojogh, Benyamin and Crowley, Mark and Karray, Fakhri and Ghodsi, Ali
Springer, 2024
Auto-Regressive Masked Diffusion Models
Karami, Mahdi, Ghodsi, Ali
International Conference on Artificial Intelligence and Statistics (AISTATS), 2026
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
Karami, Mahdi, Ghodsi, Ali
NeurIPS, 2024
Qdylora: Quantized dynamic low-rank adaptation for efficient large language model tuning
Rajabzadeh, Hossein, Valipour, Mojtaba, Zhu, Tianshu, Tahaei, Marzieh, Kwon, Hyock Ju, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
emnlp-industry, 2024
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
Kavehzadeh, Parsa, Valipour, Mojtaba, Tahaei, Marzieh, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
Findings of the Association for Computational Linguistics: EACL, 2024
Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification
Tahaei, Marzieh, Jafari, Aref, Rashid, Ahmad, Alfonso-Hermelo, David, Bibi, Khalil, Wu, Yimeng, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
Findings of the Association for Computational Linguistics: NAACL, 2024
S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models
Kavehzadeh, Parsa, Pourreza, Mohammadreza, Valipour, Mojtaba, Zhu, Tinashu, Bai, Haoli, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
arXiv preprint arXiv:2407.01955, 2024
Echoatt: Attend, copy, then adjust for more efficient large language models
Rajabzadeh, Hossein, Jafari, Aref, Sharma, Aman, Jami, Benyamin, Kwon, Hyock Ju, Ghodsi, Ali, Chen, Boxing, Rezagholizadeh, Mehdi
Efficient Natural Language and Speech Processing (ENLSP-IV) workshop, 2024
Do we need Label Regularization to Fine-tune Pre-trained Language Model
Kobyzev, Ivan, Jafari, Aref, Rezagholizadeh, Mehdi, Li, Tianda, Do-Omri, Alan, Lu, Peng, Ghodsi, Ali, Poupart, Pascal
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2023
Sortednet, a place for every network and every network in its place: Towards a generalized solution for training many-in-one neural networks
Valipour, Mojtaba, Rezagholizadeh, Mehdi, Rajabzadeh, Hossein, Tahaei, Marzieh, Chen, Boxing, Ghodsi, Ali
arXiv preprint arXiv:2309.00255, 2023
When chosen wisely, more data is what you need: A universal sample-efficient strategy for data augmentation
Kamalloo, Ehsan, Rezagholizadeh, Mehdi, Ghodsi, Ali
arXiv preprint arXiv:2203.09391, 2022
Theoretical Connection between Locally Linear Embedding, Factor Analysis, and Probabilistic PCA.
Ghojogh, Benyamin, Ghodsi, Ali, Karray, Fakhri, Crowley, Mark
Canadian AI, 2022
KroneckerBERT: Significant compression of pre-trained language models through kronecker decomposition and knowledge distillation
Tahaei, Marzieh, Charlaix, Ella, Nia, Vahid, Ghodsi, Ali, Rezagholizadeh, Mehdi
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022
Dylora: Parameter efficient tuning of pre-trained models using dynamic search-free low-rank adaptation
Valipour, Mojtaba, Rezagholizadeh, Mehdi, Kobyzev, Ivan, Ghodsi, Ali
arXiv preprint arXiv:2210.07558, 2022
Continuation kd: Improved knowledge distillation through the lens of continuation optimization
Jafari, Aref, Kobyzev, Ivan, Rezagholizadeh, Mehdi, Poupart, Pascal, Ghodsi, Ali
Findings of the Association for Computational Linguistics: EMNLP 2022, 2022
CNN and deep sets for end-to-end whole slide image representation learning
Hemati, Sobhan, Kalra, Shivam, Meaney, Cameron, Babaie, Morteza, Ghodsi, Ali, Tizhoosh, Hamid
Medical Imaging with Deep Learning, 2021
Knowledge distillation by utilizing backward pass knowledge in neural networks
Jafari, Aref, Rezagholizadeh, Mehdi, Ghodsi, Ali
Efficient Natural Language and Speech Processing (ENLSP workshop), 2021
Lakehouse: a new generation of open platforms that unify data warehousing and advanced analytics
Armbrust, Michael, Ghodsi, Ali, Xin, Reynold, Zaharia, Matei
Proceedings of CIDR, 2021
Annealing knowledge distillation
Jafari, Aref, Rezagholizadeh, Mehdi, Sharma, Pranav, Ghodsi, Ali
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 2021
Not far away, not so close: Sample efficient nearest neighbour data augmentation via minimax
Kamalloo, Ehsan, Rezagholizadeh, Mehdi, Passban, Peyman, Ghodsi, Ali
arXiv preprint arXiv:2105.13608, 2021
Symbolicgpt: A generative transformer model for symbolic regression
Valipour, Mojtaba, You, Bowen, Panju, Maysum, Ghodsi, Ali
arXiv preprint arXiv:2106.14131, 2021
How to select one among all? an extensive empirical study towards the robustness of knowledge distillation in natural language understanding
Li, Tianda, Rashid, Ahmad, Jafari, Aref, Sharma, Pranav, Ghodsi, Ali, Rezagholizadeh, Mehdi
Findings of the Association for Computational Linguistics: EMNLP 2021, 2021
Pro-KD: Progressive distillation by following the footsteps of the teacher
Rezagholizadeh, Mehdi, Jafari, Aref, Salad, Puneeth, Sharma, Pranav, Pasand, Ali Saheb, Ghodsi, Ali
Proceedings of the 29th International Conference on Computational Linguistics, 2022, 2021
Universal-KD: Attention-based output-grounded intermediate layer knowledge distillation
Wu, Yimeng, Rezagholizadeh, Mehdi, Ghaddar, Abbas, Haidar, Md Akmal, Ghodsi, Ali
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021
Fully Convolutional Networks in Localization and Classification of Cell Nuclei
Bidart, Rene, Gangeh, Mehrdad J, Peikari, Mohammad, Salama, Sherine, Nofech-Mozes, Sharon, Nofech, Sharon, Martel, Anne L, Ghodsi, Ali
, 2019
Robust locally-linear controllable embedding
Banijamali, Ershad, Shu, Rui, Bui, Hung, Ghodsi, Ali, others
International Conference on Artificial Intelligence and Statistics, 2018
Localization and classification of cell nuclei in post-neoadjuvant breast cancer surgical specimen using fully convolutional networks
Bidart, Rene, Gangeh, Mehrdad J, Peikari, Mohammad, Salama, Sherine, Nofech-Mozes, Sharon, Martel, Anne L, Ghodsi, Ali
Medical Imaging 2018: Digital Pathology, 2018
Distance correlation autoencoder
Wang, Rick, Karimi, Amir-Hossein, Ghodsi, Ali
2018 International Joint Conference on Neural Networks (IJCNN), 2018
Nonnegative matrix factorization using autoencoders and exponentiated gradient descent
El Khatib, Alaa, Huang, Shimeng, Ghodsi, Ali, Karray, Fakhri
2018 International Joint Conference on Neural Networks (IJCNN), 2018
Generative mixture of networks
Banijamali, Ershad, Ghodsi, Ali, Popuart, Pascal
2017 International Joint Conference on Neural Networks (IJCNN), 2017
Fast spectral clustering using autoencoders and landmarks
Banijamali, Ershad, Ghodsi, Ali
International Conference Image Analysis and Recognition, 2017
Discovery radiomics via a mixture of deep convnet sequencers for multi-parametric MRI prostate cancer classification
Karimi, Amir-Hossein, Chung, Audrey G, Shafiee, Mohammad Javad, Khalvati, Farzad, Haider, Masoom A, Ghodsi, Ali, Wong, Alexander
Image Analysis and Recognition: 14th International Conference, ICIAR 2017, Montreal, QC, Canada, July 5--7, 2017, Proceedings 14, 2017
Semi-supervised dictionary learning based on hilbert-schmidt independence criterion
Gangeh, Mehrdad J, Bedawi, Safaa MA, Ghodsi, Ali, Karray, Fakhri
Image Analysis and Recognition: 13th International Conference, ICIAR 2016, in Memory of Mohamed Kamel, Povoa de Varzim, Portugal, July 13-15, 2016, Proceedings 13, 2016
A dimension-independent generalization bound for kernel supervised principal component analysis
Ashtiani, Hassan, Ghodsi, Ali
Feature Extraction: Modern Questions and Challenges, 2015
Learning the Structure of Sum-Product Networks via an SVD-based Algorithm.
Adel, Tameem, Balduzzi, David, Ghodsi, Ali
UAI, 2015
Manifold unfolding by isometric patch alignment with an application in protein structure determination
Tadavani, Pooyan Khajehpour, Alipanahi, Babak, Ghodsi, Ali
Perspectives on Big Data Analysis: Methodologies and Applications, 2014
Distributed column subset selection on mapreduce
Farahat, Ahmed K, Elgohary, Ahmed, Ghodsi, Ali, Kamel, Mohamed S
2013 IEEE 13th International Conference on Data Mining, 2013
Protein structure by semidefinite facial reduction
Alipanahi, Babak, Krislock, Nathan, Ghodsi, Ali, Wolkowicz, Henry, Donaldson, Logan, Li, Ming
Research in Computational Molecular Biology: 16th Annual International Conference, RECOMB 2012, Barcelona, Spain, April 21-24, 2012. Proceedings 16, 2012
Adapting component analysis
Dorri, Fatemeh, Ghodsi, Ali
2012 IEEE 12th International Conference on Data Mining, 2012
An efficient greedy method for unsupervised feature selection
Farahat, Ahmed K, Ghodsi, Ali, Kamel, Mohamed S
2011 IEEE 11th International Conference on Data Mining, 2011
Robust locally linear embedding using penalty functions
Winlaw, Manda, Dehkordy, Leila Samimi, Ghodsi, Ali
The 2011 International Joint Conference on Neural Networks, 2011
Parameter selection for smoothing splines using Stein's unbiased risk estimator
Seifzadeh, Sepideh, Rostami, Mohammad, Ghodsi, Ali, Karray, Fakhreddine
The 2011 International Joint Conference on Neural Networks, 2011
Rare class classification by support vector machine
He, He, Ghodsi, Ali
2010 20th International Conference on Pattern Recognition, 2010
Learning an affine transformation for non-linear dimensionality reduction
Tadavani, Pooyan Khajehpour, Ghodsi, Ali
Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2010, Barcelona, Spain, September 20-24, 2010, Proceedings, Part II 21, 2010
Distance metric learning vs. fisher discriminant analysis
Alipanahi, Babak, Biggs, Michael, Ghodsi, Ali, others
Proceedings of the 23rd national conference on Artificial intelligence, 2008
Nonnegative matrix factorization via rank-one downdate
Biggs, Michael, Ghodsi, Ali, Vavasis, Stephen
Proceedings of the 25th International Conference on Machine learning, 2008
Scalable Action Respecting Embedding.
Biggs, Michael, Ghodsi, Ali, Wilkinson, Dana F, Bowling, Michael H
ISAIM, 2008
Subjective localization with action respecting embedding
Bowling, Michael, Wilkinson, Dana, Ghodsi, Ali, Milstein, Adam
Robotics Research: Results of the 12th International Symposium ISRR, 2007
Subjective mapping
Bowling, Michael, Wilkinson, Dana, Ghodsi, Ali
PROCEEDINGS OF THE NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2006
Semi-Supervised Representation Learning based on Probabilistic Labeling
, 2006
Tangent-corrected embedding
Ghodsi, Ali, Huang, Jiayuan, Southey, Finnegan, Schuurmans, Dale
2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 2005
Action respecting embedding
Bowling, Michael, Ghodsi, Ali, Wilkinson, Dana
Proceedings of the 22nd international conference on Machine learning, 2005
Learning Subjective Representations for Planning.
Wilkinson, Dana F, Bowling, Michael H, Ghodsi, Ali
IJCAI, 2005
Transformation-invariant embedding for image analysis
Ghodsi, Ali, Huang, Jiayuan, Schuurmans, Dale
Computer Vision-ECCV 2004: 8th European Conference on Computer Vision, Prague, Czech Republic, May 11-14, 2004. Proceedings, Part IV 8, 2004
Efficient parameter selection for system identification
Ghodsi, Ali
IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS'04., 2004
Regularized greedy importance sampling
Southey, Finnegan, Schuurmans, Dale, Ghodsi, Ali
Advances in Neural Information Processing Systems, 2002
A novel greedy algorithm for Nystrom approximation
Farahat, Ahmed, Ghodsi, Ali, Kamel, Mohamed
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics,
Greedy Nystrom Approximation
Farahat, Ahmed K, Kamel, Mohamed S, Ghodsi, Ali
,
Kolmogorov complexity vector: A novel data representation
,
News
-
Positions:
We are seeking passionate and motivated PhD students to join our research projects. Learn more on the Prospective Students page.
-
Teaching (Fall 2026 & Winter 2027):
I will teach Deep Learning (STAT 940) and Statistical Learning — Classification (STAT 841) in Fall 2026 and Winter 2027.
-
New Book Published:
Our new textbook Elements of Deep Learning (Ghojogh & Ghodsi, Springer, 2026) is now published. View on Springer.
