Martin Ferianc
@MartinFerianc
Followers
196
Following
556
Media
13
Statuses
178
I like machine learning, uncertainty quantification and cats 🐈.
City of London, London
Joined January 2019
I can highly recommend applying to @HLForum - I went last year and in 2019 and it was an amazing experience both times.
Applications for young researchers (undergrad, PhD or postdoc students) to attend the 2025 Heidelberg Laureate Forum @HLForum are now open. I love interacting with the young researchers there, and I'm hoping to be able to go this year, after not being able attend the last few
1
6
41
"Large language models surpass human experts in predicting neuroscience results" w @ken_lxl and https://t.co/YOhCmQlJsu. LLMs integrate a noisy yet interrelated scientific literature to forecast outcomes. https://t.co/49WYirBdBv 1/8
15
167
670
Our SAE framework enables the exploration of single-architecture ensemble neural network designs, achieving competitive accuracy and confidence calibration while reducing compute operations or parameter count by up to 1.5–3.7×. See
github.com
YAMLE: Yet Another Machine Learning Environment. Contribute to martinferianc/yamle development by creating an account on GitHub.
0
0
0
Excited to attend #BMVC2024 in Glasgow 🏴, where I had the opportunity to present our paper: SAE: Single Architecture Ensemble Neural Networks https://t.co/0WtU3brDZs
1
1
9
Paper alert📢 We report interpretable, uncertainity-optimised deep learning model to predict the printability of formulations. Full link access https://t.co/AdAMnnvBZM
0
7
18
A topic I regularly talk about with doctoral students is how to organize a PhD. It can be overwhelming to keep track of all the papers, research ideas, reviews, different collaborations, and so on. So I took some notes on how I organized my PhD:
davidstutz.de
A PhD can be a difficult endeavour. While becoming an expert in tackling a specific problems, it is easy to lose track of things: Have I read this paper before? What was the paper saying? Why did we...
6
44
226
Systematic evaluation of noise's impact on neural network performance. Offers insights for optimizing performance across various settings. Demonstrates the potential of combining noises for improved domain-specific results.
1
0
0
Key Highlights: Investigates how noise perturbations impact neural network calibration and generalisation. Identifies which perturbations are helpful and under what conditions. Emphasizes the need to customise noise for specific domains.
1
0
0
I am thrilled to share our latest paper, "Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks
https://t.co/Mq88BKttB3," published in @TmlrOrg, This work is a collective effort by @OBohdal , @tmh31, @mrd_rodrigues and myself :).
openreview.net
Enhancing the generalisation abilities of neural networks (NNs) through integrating noise such as MixUp or Dropout during training has emerged as a powerful and adaptable technique. Despite the...
3
6
30
"Large language models surpass human experts in predicting neuroscience results" w @ken_lxl and https://t.co/YOhCmQlJsu. LLMs integrate a noisy yet interrelated scientific literature to forecast outcomes. https://t.co/krtvdDqj5Q 1/6
arxiv.org
Scientific discoveries often hinge on synthesizing decades of research, a task that potentially outstrips human information processing capacities. Large language models (LLMs) offer a solution....
20
135
381
It already implements many models, methods, and datasets, so you can quickly compare your new approach to existing ones. Check out:
github.com
YAMLE: Yet Another Machine Learning Environment. Contribute to martinferianc/yamle development by creating an account on GitHub.
0
0
0
Try YAMLE to streamline the process! It includes a modular design and command-line interface, making it easy to experiment with different models and methods. It also integrates with popular PyTorch-based libraries for training, hyperparameter optimisation, and logging.
0
0
0
Introducing YAMLE: Yet another machine learning environment 🚀. Are you tired of reimplementing the same boilerplate code for every new machine learning model, method or project?
2
1
2
Introducing YAMLE: Yet another machine learning environment 🚀. Are you tired of reimplementing the same boilerplate code for every new machine learning model, method or project?
2
1
2
How predictable is neuroscience? Can LLMs outperform humans? Please participate in the https://t.co/YOhCmQlJsu survey to help us find out. You choose between two versions of a neuro abstract: the original vs. one with altered results. Which is which? https://t.co/863gHyKNMf 1/2
braingpt.org
This is the homepage for BrainGPT, a Large Language Model tool to assist neuroscientific research.
2
43
67
#IncaseYouMissedIt our amazing PhD student @MartinFerianc recently attended the @HLForum where he presented his research on making #ArtificialIntelligence more practical and trustworthy💭 Watch Martin's presentation and read more about his experience ⬇
ucl.ac.uk
Martin Ferianc, PhD student within the Institute of Communications and Connected Systems in the Department of Electrical and Electronic Engineering, recently attended the 10th annual Heidelberg
0
3
7
#InCaseYouMissedIt Check out our latest article on our PhD Student @MartinFerianc and his unforgettable experience at #HLF23 which brings together the most exceptional mathematicians and computer scientists of our generations 🧠
🗣️Our amazing PhD student @MartinFerianc recently attended the @HLForum where he presented his research on making #ArtificialIntelligence more practical and trustworthy💭 Read about Martin's experience at #HLF23, including meeting the inspiring @vgcerf
https://t.co/4p5jW8ooIv
0
1
3
👏 It's great to see our PhD student @MartinFerianc presenting his impactful research at #HLF23 - read about his experience & watch his "poster flash" presentation on his work below ⬇
🗣️Our amazing PhD student @MartinFerianc recently attended the @HLForum where he presented his research on making #ArtificialIntelligence more practical and trustworthy💭 Read about Martin's experience at #HLF23, including meeting the inspiring @vgcerf
https://t.co/4p5jW8ooIv
0
1
3
🗣️Our amazing PhD student @MartinFerianc recently attended the @HLForum where he presented his research on making #ArtificialIntelligence more practical and trustworthy💭 Read about Martin's experience at #HLF23, including meeting the inspiring @vgcerf
https://t.co/4p5jW8ooIv
0
1
6