Nicola Bernini

# Procedure ## 1. Preprocessing ### 1.1 Project into Grid Goals - Removing Ego Perspective so to work in BEV - Introduce Spatial Quantization ### 1.2 Compute Statistics on Spatial...

# Processing Strategy - This method relies on a specifically designed Region Proposal Network - One of the most famous improvement in Object Detection Research, introduced in [Faster R-CNN: Towards...

# Comparison with other Approaches - Other approaches working on Point Cloud typically require a pre-processing step to transform it into 3D Voxel or RGB-like Image hence a `WxHxC` Tensor...

# Key Points ## 1. Intelligence - Key problem: define intelligence - No unique definition, even for humans, not to mention for AI - Some key aspects here 1. Intelligence...

# Analysis ## Identified key issue - Autonomous driving requires perception - Current Perception SOTA results seem to be promising for a product but SOTA is achieved outside of the...

# Generative Models and PDF - Let's consider a **target domain** - E.g. a high dimensional domain like the `D`: *domain of images* ## Discriminative Model - Description: let's assume...

# Examples of Generative Models ## VAE  - Specifically the **Decoder Network** connecting Latent Space to Output Space - The **Encoder Network** is used for training purpose - Generation...

# Possible Domain of Applications - Drug Discovery, Proteins, Chemicals, ... - Bioinformatics - Finance - Social Networks

# Overview Performing Graph Analysis, which means solving some Graph Specific Problems, can allow to solve more abstract problems related to Data Analysis ## Graph Analysis Specific Tasks - Link...

# Traditional Tools - Kernels ## Kernel Methods ### Pro - Work well in estimating Graph Similarity related to Graphs of different dimension ### Con - Limited Scalability with respect...