Gokhan - Machine learning tutor - London
Gokhan - Machine learning tutor - London

One of our best tutors. Quality profile, experience in their field, verified qualifications and a great response time. Gokhan will be happy to arrange your first Machine learning lesson.

Gokhan

One of our best tutors. Quality profile, experience in their field, verified qualifications and a great response time. Gokhan will be happy to arrange your first Machine learning lesson.

  • Rate $122
  • Response 1h
  • Students

    Number of students Gokhan has accompanied since arriving at Superprof

    50+

    Number of students Gokhan has accompanied since arriving at Superprof

Gokhan - Machine learning tutor - London
  • 4.9 (28 reviews)

$122/h

Contact
  • Machine learning

Machine Learning with a PhD researcher: theory, maths and proofs, supervised and unsupervised methods, deep learning, model evaluation — MSc and PhD coursework, dissertations, papers

  • Machine learning

Lesson location

Ambassador

One of our best tutors. Quality profile, experience in their field, verified qualifications and a great response time. Gokhan will be happy to arrange your first Machine learning lesson.

About Gokhan

I'm Dr Gokhan Guler. I hold a PhD in engineering and computer science and I'm an active machine-learning researcher at the University of Reading, working on meta-learning and foundation-model efficiency with top-tier venues as the target — so I'm inside the literature, not describing it from memory. My day job is Principal Data & AI Architect: I design enterprise ML and GenAI systems, which means I also know what happens to a model after the notebook — pipelines, monitoring, cost and governance. I'm certified across AWS, GCP and Azure, and I have hands-on experience fine-tuning and evaluating large language models.

I've taught for more than twenty years at undergraduate and postgraduate level and delivered over 2,000 hours of one-to-one AI and ML tutoring since 2017.

My teaching runs on derivations and code together: we write the maths out until the intuition lands, then implement it and test whether it behaves the way the theory predicts. I'm equally happy slowing down over a gradient derivation or arguing about whether your evaluation protocol would survive peer review. Students range from second-year undergraduates meeting regression for the first time to PhD candidates preparing a submission.

Away from work you'll find me with my family, who are my biggest supporters in all of this.

See more

About the lesson

  • Elementary School
  • Middle School
  • High School
  • +12
  • levels :

    Elementary School

    Middle School

    High School

    Première

    Terminale

    College

    Adult Education

    Masters/ Graduate School

    Doctorate

    MBA

    Beginner

    Intermediate

    Advanced

    Proficient

    Children

  • English

All languages in which the lesson is available :

English

I teach Machine Learning to university students (undergraduate to PhD), researchers, and professionals moving into ML engineering or data science. This is the theory-and-rigour side of my teaching: the maths under the methods, why a model generalises or fails, and research-quality work.

WHAT WE WORK ON

- Foundations and maths — linear algebra, calculus and probability for ML, optimisation and gradient descent, convexity, the bias-variance trade-off, generalisation bounds, regularisation, and the proof-based questions that ML exams ask.

- Supervised learning — linear and logistic regression, k-NN, decision trees, ensembles (random forests, gradient boosting, XGBoost), SVMs and kernels, Naive Bayes, Gaussian processes, online learning.

- Unsupervised and dimensionality reduction — k-means and hierarchical clustering, Gaussian mixtures and EM, PCA, t-SNE and UMAP, anomaly detection.

- Probabilistic modelling and statistics — generalised linear models, Bayesian inference and MCMC, Bayesian networks, hidden Markov models, hierarchical models, stochastic processes, time-series modelling.

- Deep learning — MLPs and backpropagation from first principles, CNNs, RNNs and LSTMs, attention and transformers, in PyTorch and TensorFlow; NLP and computer vision; meta-learning and few-shot learning, which is my own research area.

- Evaluation done properly — cross-validation, training and test error, metric choice, class imbalance, data leakage, statistical significance, ablations, reproducibility. This is where most dissertations lose marks.

- From notebook to production — pipelines, feature stores, experiment tracking, monitoring and drift, and deployment on AWS, GCP or Azure; certification preparation for AWS Certified Machine Learning Engineer, Azure AI Engineer and Google Professional ML Engineer.

- Research supervision — framing a research question, designing experiments, reading and positioning against the literature, writing up, responding to reviewers, and targeting conferences and journals. I'm going through this myself, so the advice is current.

RECENT STUDENT WORK
A proof-based supervised-learning exam (k-NN, decision trees, online learning, Gaussian processes) · an LSTM dissertation comparing Word2Vec and TF-IDF embeddings in TensorFlow and Keras · ML algorithm implementation and evaluation in Python and R, from backpropagation to cross-validation · a neural network forecasting stock returns for an MSc Finance Analytics project · a flight-booking chatbot with scikit-learn and NLTK.

Students have come from Oxford, Imperial College London, King's College London, UCL, Manchester, Bristol, Queen Mary, Westminster, Reading and Maastricht, on modules including Machine Learning, Computational Intelligence, Big Data and Deep Learning, and Advanced Computer Science.

HOW SESSIONS RUN
Online, with screen-sharing, live coding in Jupyter or Colab, and derivations worked through on a shared whiteboard when the maths needs it. You keep the notebook and notes after every session. The first (free) session is a diagnostic: we map your module, exam or thesis against your deadlines and agree a plan. I reply within a few hours.

I help you understand and build your own work — the code, the analysis and the writing are yours; I supervise, explain and challenge.

See more

Rates

Rate

  • $122

Pack rates

  • 5 h: $609
  • 10 h: $1218

online

  • $122/h

Other tutors in Machine learning

  • Arash

    Toronto & online

    5 (17 reviews)
    • $90/h
  • Moe

    Edmonton & online

    5 (11 reviews)
    • $80/h
    • 1st lesson free
  • Ammar

    Montréal & online

    5 (15 reviews)
    • $25/h
    • 1st lesson free
  • Ryan

    Victoria & online

    5 (6 reviews)
    • $70/h
  • Pedram

    Burnaby & online

    5 (16 reviews)
    • $90/h
    • 1st lesson free
  • Farhad

    Vancouver & online

    5 (14 reviews)
    • $59/h
  • Ayo

    Toronto & online

    5 (6 reviews)
    • $20/h
    • 1st lesson free
  • Muzkkir

    Mississauga & online

    5 (8 reviews)
    • $25/h
    • 1st lesson free
  • Mobina

    Vancouver & online

    5 (17 reviews)
    • $70/h
  • Ayaan

    Toronto & online

    4.9 (27 reviews)
    • $20/h
    • 1st lesson free
  • Purva

    Toronto & online

    5 (7 reviews)
    • $28/h
    • 1st lesson free
  • Vrutti

    Mississauga & online

    5 (4 reviews)
    • $40/h
    • 1st lesson free
  • Pankti

    Windsor & online

    5 (4 reviews)
    • $70/h
    • 1st lesson free
  • Joao

    Vancouver & online

    5 (4 reviews)
    • $50/h
    • 1st lesson free
  • Anish

    Waterloo & online

    5 (7 reviews)
    • $30/h
    • 1st lesson free
  • Anirudh

    Ottawa & online

    5 (5 reviews)
    • $27/h
    • 1st lesson free
  • Ashita

    Ottawa & online

    5 (3 reviews)
    • $45/h
    • 1st lesson free
  • Maya

    Vancouver & online

    5 (7 reviews)
    • $15/h
    • 1st lesson free
  • Elias

    Montréal & online

    5 (2 reviews)
    • $45/h
  • Jatin

    Ottawa & online

    5 (4 reviews)
    • $50/h
    • 1st lesson free
  • More Machine learning tutors