Skip to content

Instantly share code, notes, and snippets.

View brando90's full-sized avatar
🎯
Focusing

Brando Miranda brando90

🎯
Focusing
45 followers · 42 following
View GitHub Profile
@brando90
brando90 / abt
Created June 15, 2021 21:16 — forked from neel-krishnaswami/abt
Abstract binding trees implementation
(* -*- mode: ocaml; -*- *)
module type FUNCTOR = sig
type 'a t
val map : ('a -> 'b) -> 'a t -> 'b t
end
type 'a monoid = {unit : 'a ; join : 'a -> 'a -> 'a}
type var = string
@brando90
brando90 / cartpole.ipynb
Created February 15, 2019 23:09 — forked from tamlyn/cartpole.ipynb
OpenAI Gym CartPole-v1 with Pytorch 1.0
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@brando90
brando90 / Policy Gradient with Cartpole and PyTorch (Medium Version).ipynb
Created February 15, 2019 22:44
Solution to the Cartpole problem with policy gradients published on Medium
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@brando90
brando90 / Deep Math.md
Created November 27, 2018 04:24 — forked from shagunsodhani/Deep Math.md
Notes for Deep Math paper

Deep Math: Deep Sequence Models for Premise Selection

Introduction

  • Automated Theorem Proving (ATP) - Attempting to prove mathematical theorems automatically.
  • Bottlenecks in ATP:
    • Autoformalization - Semantic or formal parsing of informal proofs.
    • Automated Reasoning - Reasoning about already formalised proofs.
  • Paper evaluates the effectiveness of neural sequence models for premise selection (related to automated reasoning) without using hand engineered features.
  • Link to the paper