Tameem Adel

Home | Publications | Professional Service | Collaborators| Interests

  • tameem.hesham@gmail.com
  • tah47 at cam dot ac dot uk

I am a research fellow in the Machine Learning Group at University of Cambridge, advised by Zoubin Ghahramani. Before that, I was a postdoctoral researcher at the Amsterdam Machine Learning Lab (AMLAB), advised by Max Welling.

My main research interests are circulated around probabilistic graphical models (PGMs) -especially sum-product networks-, Bayesian learning and inference, deep learning, medical applications of machine learning, and domain adaptation. I have also worked on developing transparent machine learning algorithms and on providing explanations of decisions taken by deep models.

NEWS. May 2018: Had a paper accepted to ICML 2018.

Ongoing collaborations include works with Max Welling and his Machine Learning Lab at University of Amsterdam (with which I was recently affiliated). The first Amsterdam project is focussed on ABC (Approximate Bayesian computation) algorithms, and the second is about classification of brain MRI scans using unsupervised representations. Another appreciated collaboration is the one with Alexander Wong from University of Waterloo, which involves works on learning with weak supervision and domain adaptation. The latter collaboration has begun during my PhD at University of Waterloo.

Other projects include structure and parameter learning algorithms for sum-product networks (involving collaborations with colleagues from CMU), and on unsupervised feature learning based on principles from group representation theory.

My PhD was at University of Waterloo, Waterloo, ON, Canada, co-supervised by Ali Ghodsi. Previous posts include hp enterprise services (2 years as a software engineer), Orange Labs (1 year as a research engineer) and, during my PhD, a 6-month internship at IBM Research in Zurich.

“Probability is orderly opinion, and inference from data is nothing other than the revision of such opinion in the light of relevant new information.”
Edwards et al. (1963).



      • Discovering Interpretable Representations for Both Deep Generative and Discriminative Models. [pdf]
        35th International Conference on Machine Learning (ICML 2018: Oral).
        Tameem Adel, Zoubin Ghahramani, Adrian Weller


    Journal Articles / Book Chapters
    • 3D Scattering Transforms for Disease Classification in Neuroimaging. [pdf]
      Neuroimage Clinical, 2017.
      Tameem Adel, Taco Cohen, Matthan Caan, Max Welling
      • Learning Bayesian Networks with Incomplete Data by Augmentation. [pdf]
        31st AAAI Conference on Artificial Intelligence (AAAI 2017: Oral).
        Tameem Adel, Cassio P. de Campos
      • Unsupervised Domain Adaptation with a Relaxed Covariate Shift Assumption. [pdf]
        31st AAAI Conference on Artificial Intelligence (AAAI 2017).
        Tameem Adel, Han Zhao, Alexander Wong
      • Visualizing Deep Neural Network Decisions: Prediction Difference Analysis. [pdf]
        International Conference on Learning Representations (ICLR 2017).
        Luisa M Zintgraf, Taco Cohen, Tameem Adel, Max Welling


      • Automatic Variational ABC. [ArXiv]
        ArXiv preprint 1606.08549, 2016.
        Alexander Moreno, Tameem Adel, Edward Meeds, James M. Rehg, Max Welling
      • Visualizing Deep Neural Network Decisions.
        NIPS 2016 workshop (WiML).
        Luisa M. Zintgraf, Taco S. Cohen, Tameem Adel, Max Welling
      • Collapsed Variational Inference for Sum-Product Networks. [pdf]
        33rd International Conference on Machine Learning (ICML 2016).
        Han Zhao, Tameem Adel, Geoff Gordon, Brandon Amos


      • Learning the Structure of Sum-Product Networks via an SVD-based Algorithm. [pdf]
        31st Conference on Uncertainty in Artificial Intelligence (UAI 2015).
        Tameem Adel, David Balduzzi, Ali Ghodsi
      • A Probabilistic Covariate Shift Assumption for Domain Adaptation. [pdf]
        29th AAAI Conference on Artificial Intelligence (AAAI 2015).
        Tameem Adel, Alexander Wong


      • Weakly Supervised Learning Algorithms and an Application to Electromyography. [pdf]
        PhD thesis at University of Waterloo, ON, Canada, 2014.
        Tameem Adel


        • Generative Multiple-Instance Learning Models For Quantitative Electromyography. [pdf]
          29th Conference on Uncertainty in Artificial Intelligence (UAI 2013: Oral).
          Tameem Adel, Ruth Urner, Benn Smith, Daniel Stashuk, Dan Lizotte
    Journal Articles / Book Chapters
        • Clinical Quantitative Electromyography.
          Book chapter in the book “Electrodiagnosis in New Frontiers of Clinical Research”, InTech, 2013.
          Tameem Adel, Daniel Stashuk


      • Muscle Categorization Using PDF Estimation and Naive Bayes Classification.
        (EMBC 2012: Oral).
        Tameem Adel, Benn Smith, Daniel Stashuk
      • Decomposition of Intramuscular EMG Signals Using a Knowledge-based Certainty Classifier Algorithm.
        (EMBC 2012: Oral).
        Hossein Parsaei, Daniel Stashuk, Tameem Adel


      • Tuning Graded Possibilistic Clustering by Visual Stability Analysis.
        9th International Conf. on Fuzzy Logic and Applications (WILF 2011: Oral).
        Stefano Rovetta, Francesco Masulli, Tameem Adel


    • ASCM (An Accelerated Soft C-Means Clustering Algorithm).
      10th International Conf. on Intelligent Systems Design and Applications (ISDA 2010: Oral).
      Tameem Adel, Mohamed Ismail

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s