silent-vim

sudo apt-get -y install software-properties-common
sudo add-apt-repository -y ppa:certbot/certbot
sudo apt-get -y update
sudo apt-get -y install certbot

sudo service openvpnas stop

sudo certbot certonly \
  --standalone \
  --non-interactive \

silent-vim

version: "3"

networks:

  default:

  proxy:
    external: true

volumes:

silent-vim

class Attention(Module):
    """
    Computes a weighted average of channels across timesteps (1 parameter pr. channel).
    """
    def __init__(self, attention_size, return_attention=False):
        """ Initialize the attention layer
        # Arguments:
            attention_size: Size of the attention vector.
            return_attention: If true, output will include the weight for each input token
                              used for the prediction

silent-vim

# WARNING: This docker-compose.yml is only for testing purpose.
# Parameters:
# - name: CONFLUENT_PLATFORM_VERSION
#   default: 3.0.0
#   reference: https://hub.docker.com/u/confluentinc/
# Ports:
# - description: Major ports are exposed to host computer
# - zookeeper: 2181
#      kafka1: 9091
#      kafka2: 9092

silent-vim

import torch
from torch import nn
from torch.autograd import Variable
import torch.nn.functional as F

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, n_layers=1):
        super(RNN, self).__init__()
        self.input_size = input_size
        self.hidden_size = hidden_size

silent-vim

Comprehensive Texts - Books

• Deep Learning - Goodfellow, Bengio, Courville
  • Section 1: ML basics (skipped)
  • Section 2: DL
  • Section 3: DL in practice & research
  • Summary - Notes by someone
• ⭐ Deep Learning in Neural Networks: An Overview - Schmidhuber
• [ML yearning - Andrew Ng] (http://www.mlyearning.org/): general Machine Learning skills (not fully available yet)

Courses and long reads

• A Statistical View of Deep Learning (many blog posts)

silent-vim

class attentionalLSTMCell(nn.Module):
    def __init__(self, input_size, hidden_size, num_variants):
        super(attentionalLSTMCell, self).__init__()
        self.hidden_size = hidden_size
        self.input_size = input_size
        self.num_variants = num_variants
        
        self.ih = nn.Linear(self.input_size, 4 * self.hidden_size * self.num_variants)
        self.hh = nn.Linear(self.hidden_size, 4 * self.hidden_size * self.num_variants)
        

silent-vim

package com.learndirect.tutor;

import static com.google.common.base.Charsets.UTF_8;
import static org.apache.commons.codec.binary.Base64.decodeBase64;
import static org.apache.commons.codec.binary.Base64.encodeBase64;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.util.Map;