llSourcell

yosadad
https://docs.google.com/presentation/d/1dinjf2mZ1SkRnzJo6fL-ZfGyGDBI4JWeoGsnBj7hNNg/edit?usp=sharing

llSourcell

#!/usr/bin/env python3

"""
This script allows you to manually control the simulator
using the keyboard arrows.
"""

import sys
import argparse
import pyglet

llSourcell

use std::io;
use std::process;

fn main() {
   //Step 0 - Collect data
    let x: [f64; 8] = [44.0, 46.0, 59.0, 67.0, 74.0, 85.0, 97.0, 43.0];
    let y: [f64; 8] = [1200.0, 2400.0, 3200.0, 3000.0, 5000.0, 4000.0, 6000.0, 6050.0]; 
    println!("Total profit per month");

    //Step 1 - Compute the average of X

llSourcell

Achieving warp speed with Rust

Contents:

• Number one optimization tip: don't
• Never optimize blindly
• Don't bother optimizing one-time costs
• Improve your algorithms
• CPU architecture primer
• Keep as much as possible in cache
• Keep as much as possible in registers

llSourcell

Game 1: Avoid the Hooks

Goal

• Dedicate 60 hours/week to learning a subject

Feedback System

• Pomodoro Score

Rules

• Find or Build the idea gateway

llSourcell

//
//  onehiddenlayerperceptron.cu
//  onehiddenlayerperceptron
//
//  Created by Sergei Bugrov on 8/21/17.
//  Copyright © 2017 Sergei Bugrov. All rights reserved.
//

#include <stdio.h>

llSourcell

#by MBT on StackOverflow
import numpy as np

# D_in is input dimension;
# H is hidden dimension;
# D_out is output dimension.
Batch_Size, D_in, H, D_out = 12, 1000, 100, 10

# Create random input and output data
x = np.random.randn(Batch_Size, D_in)

llSourcell

#by MBT on StackOverflow
import numpy as np

# D_in is input dimension;
# H is hidden dimension;
# D_out is output dimension.
Batch_Size, D_in, H, D_out = 64, 1000, 100, 10

# Create random input and output data
x = np.random.randn(Batch_Size, D_in)

llSourcell

#pytorch team
for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

llSourcell

#by deepmind
import tensorflow as tf
import sonnet as snt

#setup a 'module'
mlp = snt.Sequential([
    snt.Linear(1024),
    tf.nn.relu,
    snt.Linear(10),
])