A curious and creative programmer with a deep passion for learning. I focus on projects at the intersection of medicine, finance, and education, aiming to make work in these fields easier and more engaging through artificial intelligence.
Designing reliable architectures with highly optimized layers. Translating mathematical models into performant data ingestion, transformation, and automated retraining pipelines.
A comprehensive AI-driven system engineered to predict financial risk indicators and market volatility. Utilizes advanced LSTM layers and Self-Attention mechanisms combined with rigorous quantitative engineering to capture systemic changes.
class Attention(nn.Module):
def __init__(self, hidden_dim):
super().__init__()
self.weights = nn.Linear(hidden_dim, 1)
def forward(self, l_outputs):
attn_weights = F.softmax(
self.weights(l_outputs), dim=1
)
context = torch.sum(
attn_weights * l_outputs, dim=1
)
return context, attn_weights
Intelligent assistant designed to aid medical specialists in detecting early-stage pathologies. Incorporates multi-layered neural network processing of medical diagnostic imaging.
A highly customized, interactive learning framework that dynamically adapts difficulty levels and educational pathways using reinforcement learning strategies based on tracking real-time student performance.