{"id":1101,"date":"2026-07-14T11:24:13","date_gmt":"2026-07-14T11:24:13","guid":{"rendered":"https:\/\/deeplearningindaba.com\/2026\/?page_id=1101"},"modified":"2026-07-14T11:24:13","modified_gmt":"2026-07-14T11:24:13","slug":"accepted-tutorials-skills-sessions","status":"publish","type":"page","link":"https:\/\/deeplearningindaba.com\/2026\/accepted-tutorials-skills-sessions\/","title":{"rendered":"Accepted Tutorials & Skills Sessions"},"content":{"rendered":"
<\/span>\n

Accepted Tutorials & Skill Sessions<\/h1>
<\/div><\/div><\/div><\/div>
<\/div>
<\/div><\/section>\n<\/div>\n\n
\n
\n
\n

The Deep Learning Indaba (DLI) is the annual gathering of Africa\u2019s Machine Learning and AI community, dedicated to strengthening and celebrating African AI. In 2026, the Deep Learning Indaba will be held in Nigeria in August (exact dates to be announced later). The event will include keynotes, tutorials, workshops, panels, and other interactive sessions. The theme for this year's Indaba is: <\/span>Sovereign Intelligence: Africa\u2019s Path in a Frontier AI World.\u00a0<\/i><\/b><\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n<\/div>\n\n

\n
\n
\n

Accepted Tutorials<\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n\n

\n
\n
\uf0a9<\/span><\/span><\/div>

Introduction to Agentic AI: Building Conversational Agents with Persistent Memory<\/h4>

Abstract : Agentic AI, systems that hold a conversation, remember context, and act over time, is moving from research
into production. Yet most introductory material treats agents as stateless chatbots and ignores the memory that makes them useful. In this tutorial I give undergraduates from any ML background a practical, code-forward introduction to building conversational agents with persistent memory. We start from first principles: what an AI agent is, how conversational systems track state, and why a model's short-term context window is not enough. We then build a working agent in Python from scratch and give it long-term memory using vector embeddings, retrieving relevant memories on demand. To make the lesson concrete, the agent we build is a griot, a storyteller that must remember an evolving folktale across turns and sessions. Everything runs on small open models, locally, with no API key and no data leaving the machine. That keeps the session
easy to run for everyone, and it doubles as a working demonstration of sovereign, self-hostable AI. Attendees leave able to build a memory-backed agent themselves and to reason about deploying and owning one responsibly.<\/p>\n

Led by : David Agbolade <\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

\n
\n
\uf0a9<\/span><\/span><\/div>

Responsible and Sovereign AI: Fair, Trustworthy, and Context-Aware Machine Learning for Africa<\/h4>

Abstract : As artificial intelligence rapidly advances into the frontier era, questions of sovereignty, fairness, and accountability have become central to Africa\u2019s participation in the global AI ecosystem. Many responsible AI methods were developed in data-rich environments and often rely on demographic labels or assumptions that do not transfer well to African contexts, where data may be sparse, heterogeneous, or culturally nuanced. This tutorial introduces principled and practical approaches for building responsible and sovereign AI systems tailored to African realities. We begin by revisiting core foundations of responsible AI including fairness, transparency, robustness, and accountability, through the lens of low-resource and cross-cultural deployment settings. Participants will learn how bias can emerge across the machine learning pipeline and how to diagnose it using widely adopted fairness metrics such as demographic parity and equalized odds. The tutorial will also highlight emerging directions, including fairness-aware learning without demographic labels and evaluation under distribution shift. Through guided hands-on exercises and case studies spanning health risk prediction, African language technologies, and social media analysis, attendees will gain practical skills for auditing and improving model behavior. By the end of the session, participants will be equipped to design AI systems that are not only accurate but also equitable, trustworthy, and locally grounded. This tutorial directly supports the Indaba 2026 theme by strengthening technical capacity for sovereign, responsible AI development across Africa.<\/p>\n

Led by : Blessing Ogbuokiri\u00a0<\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

\n
\n
\uf0a9<\/span><\/span><\/div>

The AI Lab Partner: Agents for Biological Discovery<\/h4>

Abstract : As AI tools become integrated into the life sciences, the essential skill for the modern researcher is shifting from running static models to orchestrating \"Agentic Workflows.\" This tutorial moves beyond basic prompting to demonstrate how researchers can use AI agents as collaborative \"Lab Partners\" to handle iterative, data-driven tasks that call specialised machine learning models. <\/span>The session provides a hands-on Google Colab experience centred on a critical real-world problem: optimising protein thermal stability. Many life-saving biologicals, such as vaccines and insulin, are fragile and require a strict \"cold chain\" (2\u00b0C to 8\u00b0C) that is difficult to maintain in rural or high-temperature regions. By using agents to redesign these molecules for heat resistance, we can improve global health outcomes and industrial efficiency.<\/span><\/p>\n

Participants will learn to:<\/span>\u00a0<\/p>\n

    \n
  1. Use agents to identify and prioritise biological research targets.<\/span><\/li>\n
  2. Automate data orchestration from public repositories like UniProt.<\/span><\/li>\n
  3. Integrate specialised scientific libraries for structural analysis and stability prediction.<\/span><\/li>\n
  4. Design iterative feedback loops where agents suggest and refine sequences based on calculated metrics.<\/li>\n<\/ol>\n

    Participants will leave with a practical framework for using AI agents to navigate complex biological datasets and automate the \"drudgery\" of research. No prior biology background is required; basic Python proficiency is sufficient.<\/span><\/p>\n

    Led by : Natasha Latysheva <\/span>; Sebastian Bodenstein <\/span><\/span><\/a>; Kyle Taylor <\/span>; Adam Kosiorek <\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    Understanding Model Alignment: Concepts and Practical Steps<\/h4>

    Abstract : As artificial intelligence systems grow more capable, ensuring they behave in ways consistent with human values and intentions\u2014known as model alignment\u2014has become a central concern in AI safety. This tutorial, presented at the Deep Learning Indaba, offers an accessible, hands-on introduction to the core concepts and practical techniques for aligning modern AI models. We begin by motivating the alignment problem through real-world examples of misaligned behaviour in deployed systems, illustrating how models can produce harmful, biased, or unintended outputs even when achieving strong benchmark performance. We then introduce foundational alignment concepts, including the distinction between outer and inner alignment, reward misspecification, and goal misgeneralization. The tutorial surveys the most widely adopted alignment techniques\u2014reinforcement learning from human feedback (RLHF), direct preference optimisation (DPO), and constitutional AI\u2014explaining each method's intuition, workflow, and trade-offs in a manner accessible to participants with a working knowledge of deep learning. A significant portion of the session is dedicated to practical steps: we walk-through how-to curate preference datasets, fine-tune a language model using open-source alignment toolkits, design red-teaming exercises, and evaluate alignment using both automated and human evaluation protocols. We also address considerations especially relevant to the African AI community, including aligning models to diverse cultural values, handling low-resource languages, and building locally relevant evaluation benchmarks. The tutorial concludes by highlighting open challenges, such as scalable oversight and superalignment, and encourages participants to contribute to this rapidly evolving and globally important field.<\/span><\/p>\n

    Led by : \u00a0Michael Mollel ; Winnie Mangeni \u00a0; Innocent Charles\u00a0<\/span><\/b><\/p>\n

     <\/p>\n

    <\/a><\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    Beyond the Notebook: Mastering Cloud GPU Infrastructure for Scalable African AI <\/h4>

    Abstract: While Google Colab has democratized initial access to machine learning across Africa, its infrastructure limitations, such as session timeouts, lack of persistent storage, restricted environment control, and limited compute, stifle the transition from academic experimentation to production-ready AI. True \u201cSovereign Intelligence\u201d requires African researchers to graduate from managed notebooks to dedicated, localized cloud infrastructure. This two-hour tutorial introduces participants to the
    fundamentals of developing on sovereign African GPU Virtual Machines (VMs). We begin by identifying the \u201cColab Ceiling\u201d and detailing the core architectural advantages of dedicated VMs, including persistent environments, massive data pipelines, custom CUDA configurations, and specialized workloads like fine-tuning open-source LLMs, Retrieval-Augmented Generation (RAG), and multimodal generative AI media pipelines (image, music, and film). To ensure an interactive experience, every participant will receive a $5 credit to log into an active aghcloud.ai African-hosted GPU instance live during the session. Using the AGH GPU Optimizer tool, attendees will learn how to analyze their specific workload requirements and match them to the most cost-effective hardware. By the end of this tutorial, students and researchers will possess the practical DevOps skills necessary to optimize, deploy, monitor, and scale sovereign AI applications entirely within Africa.<\/p>\n

    Led by : Chisom Chinwuba \u00a0; Sheriff Issaka \u00a0; Opemipo Durodola\u00a0<\/span><\/b><\/p>\n

     <\/p>\n

    <\/a><\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    The Math Behind Neural Networks<\/h4>

    Abstract: This tutorial offers a deep dive into the mathematics of neural networks, the building blocks of contemporary AI. Starting from an intuitive understanding of 'what it means for a machine to learn,' the tutorial introduces essential concepts such as cost functions and gradient descent, before presenting the artificial neuron and the feedforward mechanism. The centrepiece is backpropagation: participants work through the gradients themselves, guided by slides that reveal the derivations progressively, ensuring active engagement rather than passive reception. The concepts of memoization and tensor dimensions are also addressed. By the end, participants will have a good understanding of how neural networks are trained. The tutorial closes with a live demo of TensorFlow Playground in which we\u00a0 explore how architecture choices (depth, width, activation functions) shape the resulting decision boundaries. A follow-up skills session, \"Code a Neural Network From Scratch\" is\u00a0 a hands-on session that complements the theory.<\/span><\/p>\n

    Led by : Pelumi Victor \u00a0; Catherine Essuman\u00a0<\/span><\/b><\/p>\n

     <\/p>\n

    <\/a><\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    Building Faster Transformers with Triton: A Hands-On Introduction to GPU Kernel Programming <\/h4>

    Abstract: Modern Transformer models are increasingly powerful, but their real-world usefulness depends heavily on how efficiently they can be trained and served on GPU hardware. This tutorial introduces participants to GPU kernel programming with Triton through the practical goal of building faster Transformer components from the ground up. We will begin with the performance bottlenecks that commonly appear in Transformer workloads, including memory bandwidth limits, attention computation, operator overhead, and inefficient data movement. Participants will then learn the core ideas behind GPU execution, tensor layouts, parallelism, tiling, and memory hierarchy before implementing simple Triton kernels.
    The hands-on section will focus on writing, benchmarking, and optimizing kernels for common Transformer operations, gradually building toward attention-related kernels used in modern LLM systems. By the end of the tutorial, participants will understand how custom GPU kernels can improve Transformer performance, how to reason about throughput and memory efficiency, and how to begin applying Triton to their own machine learning systems research and engineering projects.<\/p>\n

    Led by : Ayomide Odumakinde \u00a0; Katherine Oluwadarasimi Olowookere ; Adeniyi Mayokun\u00a0<\/span><\/b><\/p>\n

     <\/p>\n

    <\/a><\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    Graph Neural Networks: Foundations and Applications for Real-World Networks <\/h4>

    Abstract: Many African systems are inherently relational. Mobile money transaction networks in Kenya and Uganda, electricity transmission infrastructure in South Africa and Zambia, transportation networks in Lagos and Accra, and agricultural supply chains in Morocco and Egypt all form networks of connected entities, and traditional machine learning methods, which treat samples as independent, often miss the signal carried by these connections. Graph Neural Networks (GNNs) are designed to
    learn directly from such structure, propagating information across nodes to capture relational dependencies.
    This tutorial introduces the foundations of GNNs for an audience new to graph-based learning. It covers core concepts such as message passing and two foundational architectures, the Graph Convolutional Network (GCN) and the Graph Attention
    Network (GAT). A live demonstration walks through building and training a GNN for account-level fraud detection on a subsampled mobile money transaction graph, using the MoMTSim dataset developed at Makerere University. Slides, notebooks, exercises, and reading lists will be released on a public GitHub repository after the session. Participants will leave able to represent graph-structured data, build and train basic GNN models, and recognise where such methods can be applied to challenges across finance, infrastructure, agriculture, and urban systems in their own communities and beyond.<\/p>\n

    Led by : NATARAM ODUMO ; Nwandu Christian\u00a0; Godbless James <\/span><\/b><\/p>\n

     <\/p>\n

    <\/a><\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n

    Accepted Skills Sessions<\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    Doing ML research from the margins <\/h4>

    Abstract: Getting into ML research with little or no institutional backing is hard. Getting published at top venues without a lab, an advisor, or a GPU cluster feels nearly impossible \u2014 and for most people trying from Africa, it has been exactly that. But even under those constraints, it doesn't have to stay that way. <\/span>This session is built around a simple premise: the path exists, it's navigable, and it can be made legible. We know because we have watched people like us walk it \u2014 from self-taught practitioners with no institutional affiliation, to first authors at A* venues, to PhD students at world-class programs and research scientists\/engineers at big tech companies. The trajectories are real. The moves that made them possible are identifiable. <\/span>This session reverse-engineers those moves. We will cover the mindset shifts that matter most when working without institutional support; how to find and approach mentors effectively; how to scope research problems that are tractable with limited compute and no proprietary data; how to read and engage with literature efficiently; and how to write and position work for top venues rather than defaulting to workshops and obscure journals; which matters directly when applying to competitive programs and grants. <\/span>We will be honest about the structural barriers. They are real, they are unequally distributed, and they compound. But the focus here is on what is actually within your control. <\/span>The goal is not to inspire. It's to leave you with a clearer map than we had.<\/span><\/p>\n

    Led by : Steven Kolawole\u00a0<\/span><\/b><\/p>\n

     <\/p>\n

    <\/a><\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    Building On Device AI Applications Using Gemma 3n<\/h4>

    Abstract: This one-hour skill session shows how capable language models can run locally on phones and laptops through careful model selection, conversion and quantisation. It will start with a short demo of a prebuilt mobile app so everyone sees the end result from the start. We then use the Gemma 3n family or a lightweight alternative (Qwen3.5 0.8B) as a primary case study to highlight size, latency, and capability. The session explains the core idea of quantisation: how lowering numeric precision shrinks model size and memory use while preserving much of the model\u2019s usefulness. I walk through the practical conversion and quantisation steps you need to generate a mobile-friendly GGUF or TFLite artifact, plus common pitfalls and tuning tips. Finally, I show how the quantised model is integrated into a React Native Expo project (prebuilt APKs and code provided), describe distribution options, and point to further resources. Everyone leaves with a checklist, links to the exact scripts and builds used in the demo, and a clear path to experiment with on-device models in their own projects.<\/span><\/p>\n

    Led by : Jesse-Paul Osemeke\u00a0; Daniel Onyesoh\u00a0<\/span><\/b><\/p>\n

     <\/p>\n

    <\/a><\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    Mastering the Scientific Narrative: A Practical Guide to Reading and Writing High-Impact AI Research Papers<\/h4>

    Abstract:To achieve \"Sovereign Intelligence,\" African researchers must not only build innovative models but also master the art of global scientific communication. Many young scholars in Africa possess groundbreaking ideas but face barriers in effectively deconstructing dense AI literature or structuring their findings for top-tier venues. This Skill Session is designed to bridge this gap. <\/span>We will move beyond theory to provide a systematic \"how-to\" for both consuming and producing research. The session will cover the \"3-pass\" reading strategy to extract core contributions from complex papers quickly. On the writing side, it will demystify the scientific storytelling process\u2014from crafting a compelling Abstract to presenting results that meet international standards. By equipping participants with these reusable competencies, we empower African AI agency, ensuring that our local innovations are documented, recognized, and integrated into the global frontier of AI. This session targets undergraduate and early-graduate students, providing them with a concrete blueprint for scientific success.<\/span><\/p>\n

    Led by : Castro Gb\u00eam\u00eamali\u00a0<\/span><\/b><\/a><\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n

    \n
    \n
    \uf0a9<\/span><\/span><\/div>

    Adversarial Thinking in AI Systems: Understanding and Mitigating Real-World Model Failures<\/h4>

    Abstract: Modern AI systems are increasingly deployed in high-stakes environments, yet they remain vulnerable to subtle but powerful adversarial manipulations. From evasion attacks and data poisoning to prompt injection in large language models, these vulnerabilities expose critical weaknesses in today\u2019s machine learning pipelines. <\/span>This practical session introduces participants to the core concepts of adversarial machine learning and AI security. We will explore how and why models fail, demonstrate simple attack scenarios, and discuss practical mitigation strategies that can be applied in real-world systems. <\/span>The session emphasizes building a security mindset for AI development, encouraging participants to think beyond accuracy and consider robustness, reliability, and long-term system resilience. Through guided examples and discussion, attendees will gain foundational tools to evaluate and strengthen AI systems in resource-constrained and emerging technological environments.<\/span><\/p>\n

    Led by : Manar Hamed\u00a0<\/span><\/b><\/p>\n<\/div><\/div><\/div><\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"","protected":false},"author":32,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":"","_links_to":"","_links_to_target":""},"class_list":["post-1101","page","type-page","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/deeplearningindaba.com\/2026\/wp-json\/wp\/v2\/pages\/1101","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/deeplearningindaba.com\/2026\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/deeplearningindaba.com\/2026\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/deeplearningindaba.com\/2026\/wp-json\/wp\/v2\/users\/32"}],"replies":[{"embeddable":true,"href":"https:\/\/deeplearningindaba.com\/2026\/wp-json\/wp\/v2\/comments?post=1101"}],"version-history":[{"count":3,"href":"https:\/\/deeplearningindaba.com\/2026\/wp-json\/wp\/v2\/pages\/1101\/revisions"}],"predecessor-version":[{"id":1104,"href":"https:\/\/deeplearningindaba.com\/2026\/wp-json\/wp\/v2\/pages\/1101\/revisions\/1104"}],"wp:attachment":[{"href":"https:\/\/deeplearningindaba.com\/2026\/wp-json\/wp\/v2\/media?parent=1101"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}