digitado

About digitado

https://www.digitado.com.br

Posts by :

The Future of Voice AI in Banking: Amar Kant Jha

⋅

The integration of artificial intelligence into financial services represents an operational shift for banking institutions operating across global markets. Industry implementation accelerates as financial firms utilize Generative AI to adjust user experiences across digital channels. This transition from touch-based interfaces to conversational frameworks requires oversight of system performance, rigorous security protocols, and secure data handling capabilities. Amar Kant Jha, a Lead Software Engineer with over fourteen years of experience in mobile application architecture, focuses extensively on developing iOS […]

Ver mais

Liked Liked

Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning

⋅

Graph neural networks face two fundamental challenges rooted in the linear structure of Euclidean vector spaces: (1) Current architectures represent geometry through vectors (directions, gradients), yet many tasks require matrix-valued representations that capture relationships between directions-such as how atomic orientations covary in a molecule. These second-order representations are naturally captured by points on the symmetric positive definite matrices (SPD) manifold; (2) Standard message passing applies shared transformations across edges. Sheaf neural networks address this via edge-specific transformations, but […]

Ver mais

Liked Liked
GPT-4 Has 1.8 Trillion Parameters. It Uses 2% of Them Per Token.

GPT-4 Has 1.8 Trillion Parameters. It Uses 2% of Them Per Token.

⋅

Author(s): DrSwarnenduAI Originally published on Towards AI. GPT-4 Has 1.8 Trillion Parameters. It Uses 2% of Them Per Token. DeepSeek-R1: 671 billion parameters. 37 billion active per token. DeepSeek-R1: 671 billion parameters. 37 billion active per token.The article discusses various machine learning models, focusing on their parameter count and operational efficiencies. It delves into the architecture of the Mixture of Experts (MoE), detailing how different models utilize parameters per token and how routing affects performance, emphasizing the benefits […]

Ver mais

Liked Liked

PPO agent for network control

⋅

I built a PPO-Agent to control flows inside a physical network. The agent controls the 15 control variables, which in physical world would mean how strong we are pumping the medium inside the network. It is working after 25 million environment steps. I was testing different reward functions and so far the best was something like following: reward = -1 * tanh(physical_violations_in_network) + 0.05 * tanh(violation_improvement_from_previous_step) – 0.07 * tanh(violation_deterioration_from_previous_step) I made the improvement coef and deterioration coef […]

Ver mais

Liked Liked

Photon Releases Spectrum: An Open-Source TypeScript Framework that Deploys AI Agents Directly to iMessage, WhatsApp, and Telegram

⋅

For all the progress made in AI agent development over the past few years, one fundamental problem has remained largely unsolved: most people never actually interact with agents. They live behind developer dashboards, inside specialized apps that users are asked to download, and within chat interfaces that the majority of the world’s population will never visit. The models are good. The reasoning capabilities are extraordinary. But the distribution is broken. Photon, an infrastructure company focused on reliable, low-latency […]

Ver mais

Liked Liked

The role of AI in modern forex bot development

⋅

Artificial intelligence has become a defining force in financial markets. And currency trading is no exception. The rise of the AI-powered forex bot reflects a change toward automated systems capable of processing vast amounts of market data and identifying patterns beyond the reach of manual analysis. As global foreign exchange markets operate around the clock and generate enormous streams of information, traders increasingly rely on intelligent tools that can analyse, interpret and act on market signals in real […]

Ver mais

Liked Liked

SAB-DeepLabV3+: A Semantic Segmentation Framework for Mapping Maize Waterlogging from Single-Date Multispectral Imagery

⋅

Rapid identification of maize waterlogging is essential for post-disaster agricultural assessment, but most existing methods rely on multi-temporal imagery that is often unavailable immediately after extreme rainfall events. This study proposes SAB-DeepLabV3+, a semantic segmentation model for mapping waterlogged maize from single-date multispectral imagery within pre-extracted maize planting areas. Built on DeepLabV3+, the model integrates three task-specific modules: a Spectral-Spatial Information Enhancement Module to improve feature discrimination under spectral mixing, an Adaptive Multi-Scale Pooling Module to capture heterogeneous […]

Ver mais

Liked Liked

RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings

⋅

A common strategy in transfer learning is few shot fine-tuning, but its success is highly dependent on the quality of samples selected as training examples. Active learning methods such as uncertainty sampling and diversity sampling can select useful samples. However, under extremely low-resource and class-imbalanced conditions, they often favor outliers rather than truly informative samples, resulting in degraded performance. In this paper, we introduce RADS (Reinforcement Adaptive Domain Sampling), a robust sample selection strategy using reinforcement learning (RL) […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2026