From thegradient.pub
Towards Geometric Deep Learning
0 0
Geometric Deep Learning is a term for approaches considering ML problems from the perspectives of symmetry and invariance. It provides a common blueprint for CNNs, GNNs, and Transformers. Here, we study the history of GDL from ancient Greek geometry to Graph Neural Networks.
on Nov 18
From thegradient.pub
Shape, Symmetries, and Structure: The Changing Role of Mathematics in Machine Learning Research
0 0
What is the Role of Mathematics in Modern Machine Learning? The past decade has witnessed a shift in how progress is made in machine learning. Research involving carefully designed and mathematically principled architectures result in only marginal improvements while compute-intensive and...
on Nov 16
From thegradient.pub
What's Missing From LLM Chatbots: A Sense of Purpose
0 0
LLM-based chatbots’ capabilities have been advancing every month. These improvements are mostly measured by benchmarks like MMLU, HumanEval, and MATH (e.g. sonnet 3.5, gpt-4o). However, as these measures get more and more saturated, is user experience increasing in proportion to these scores? If...
on Sep 27
From thegradient.pub
We Need Positive Visions for AI Grounded in Wellbeing
0 0
Introduction Imagine yourself a decade ago, jumping directly into the present shock of conversing naturally with an encyclopedic AI that crafts images, writes code, and debates philosophy. Won’t this technology almost certainly transform society — and hasn’t AI’s impact on us so far been a...
on Aug 3
From thegradient.pub
One Voice Detector to Rule Them All
0 1
VAD is among the most important and fundamental algorithms in any production or data preparation pipelines related to speech
on Jul 29
From thegradient.pub
Machine Learning Won't Solve Natural Language Understanding
0 0
An argument that it is time to re-think our approach to natural language understanding, since the ‘big data’ approach to NLU is implausible and both technically and theoretically flawed..
on Jul 19
From thegradient.pub
Why transformative artificial intelligence is really, really hard to achieve
0 2
A collection of the best technical, social, and economic arguments Humans have a good track record of innovation. The mechanization of agriculture, steam engines, electricity, modern medicine, computers, and the internet—these technologies radically changed the world. Still, the trend growth...
on May 16
From thegradient.pub
Financial Market Applications of LLMs
0 0
The AI revolution drove frenzied investment in both private and public companies and captured the public’s imagination in 2023. Transformational consumer products like ChatGPT are powered by Large Language Models (LLMs) that excel at modeling sequences of tokens that represent words or parts of...
on Apr 20
From thegradient.pub
A Brief Overview of Gender Bias in AI
0 1
A brief overview and discussion on gender bias in AI
on Apr 9
From thegradient.pub
0 0
Is Attention all you need? Mamba, a novel AI model based on State Space Models (SSMs), emerges as a formidable alternative to the widely used Transformer models, addressing their inefficiency in processing long sequences.
on Mar 30
From thegradient.pub
Do text embeddings perfectly encode text?
0 0
'Vec2text' can serve as a solution for accurately reverting embeddings back into text, thus highlighting the urgent need for revisiting security protocols around embedded data.
on Mar 14
From thegradient.pub
0 0
On fish counting – a complex sociotechnical problem in a field that is going through the process of digital transformation.
on Dec 17, 2023
From thegradient.pub
Introduction to Artificial Life for People who Like AI
0 0
The AI enthusiast's Introduction to Artificial Life: old ties between AI and ALife, and what makes ALife research special.
on Dec 14, 2023
From thegradient.pub
Stanford's Human-Centered AI Launch Symposium
0 0
Will artificial intelligence replace or augment humanity?
on Nov 30, 2023
From thegradient.pub
Gaussian Processes, not quite for dummies
0 0
I recall always having this vague impression about Gaussian Processes (GPs) being a magical algorithm that is able to define probability distributions over sets of functions, but I had always procrastinated reading up on the details. It's not completely my fault though! Whenever I Google...
on Nov 13, 2023
From thegradient.pub
Machine Translation Shifts Power
0 0
On how the creation, development, and deployment of machine translation technology is historically entangled with practices of surveillance and governance
on Oct 24, 2023
From thegradient.pub
Text-to-CAD: Risks and Opportunities
0 0
In the realm of AI-powered text-to-CAD, there's promise, but also a surge in subpar designs. Can we steer this technology towards better outcomes?
on Oct 20, 2023